GeekRadar / The comparison desk

Gemini 2.5 Flash vs Gemini 2.5 Pro

Catalog Differences only

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Gemini 2.5 Flash 1416.9 Gemini 2.5 Flash · 95% interval 1414.5–1419.3 · 125,457 votes · 2026-10-28

Gemini 2.5 Pro 1457.7 Gemini 2.5 Pro · 95% interval 1455.3–1460.1 · 125,307 votes · 2026-10-28

Run it locally

Inference · memory estimate

Gemini 2.5 Flash

Closed weights. No supported local deployment or GPU requirement is published.

Gemini 2.5 Pro

Closed weights. No supported local deployment or GPU requirement is published.

Gemini 2.5 Flash vs Gemini 2.5 Pro
At a glance	Models Gemini 2.5 Flash google	Models Gemini 2.5 Pro google
Release date	2025-06-17	2025-06-17
Capabilities
Context window	1,048,576 tokens	1,048,576 tokens
Maximum input	1,048,576 tokens^*	1,048,576 tokens^*
Maximum output	65,536 tokens	65,536 tokens
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Structured output	Yes^*	Yes^*
Open weights	No	No
Knowledge cutoff	2025-01	2025-01
API mode	Chat^*	Chat^*
Model type	Not reported	LLM (frontier reasoning / thinking)^*
Declared modalities	Not reported	Text, Image, Audio, Video, PDF → Text^*
Image input	Yes^*	Yes^*
PDF input	Yes^*	Yes^*
Video input	Not reported	Yes^*
Audio input	Not reported	Yes^*
Audio output	No^*	Not reported
Parallel tool calls	Yes^*	Not reported
Prompt caching	Yes^*	Yes^*
System messages	Yes^*	Yes^*
Tool choice	Yes^*	Yes^*
Web search	Yes^*	Yes^*
Model license	Proprietary	Proprietary
Detailed specifications	Specifications · 41 fields cache read input audio token cost 1.0e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost 3.0e-8^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost flex 3.0e-8^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost priority 5.4e-8^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* deprecation date 2026-10-20^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* google maps grounding cost per query 0.025^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per audio token 1.0e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per audio token batches 5.0e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per audio token priority 1.8e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token 3.0e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token batches 1.5e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token flex 1.5e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token priority 5.4e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* litellm provider vertex_ai-language-models^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* max input tokens 1,048,576^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* max output tokens 65,535^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* max tokens 65,535^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* mode chat^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per reasoning token 2.5e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token 2.5e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token batches 1.25e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token flex 1.25e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token priority 4.5e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* search context cost per query search_context_size_low 0.035^* search_context_size_medium 0.035^* search_context_size_high 0.035^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* search free requests count 1,500^* period day^* shared_group gemini-2-flash^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supported endpoints /v1/chat/completions^* /v1/completions^* /v1/batch^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supported modalities text^* image^* audio^* video^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supported output modalities text^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports audio output No^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports function calling Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports image size No^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports parallel function calling Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports pdf input Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports prompt caching Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports reasoning Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports response schema Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports system messages Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports tool choice Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports url context Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports vision Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports web search Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-flash^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*	Specifications 1 · 12 fields api providers Google AI Studio (Gemini API), Vertex AI, OpenRouter^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* context window 1M (1,048,576 tokens)^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* developer Google^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* input price 1.25^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* license Proprietary^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* max output 64K (65,536 tokens)^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* modality Text, Image, Audio, Video, PDF → Text^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* model type LLM (frontier reasoning / thinking)^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* name Gemini 2.5 Pro^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* open weights no^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* output price 10^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* release date March 2025 (preview); June 17, 2025 (GA)^* Scope and conditions native_context metadata name Convly AI Models Database^* description Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.^* generated 2026-09-22T15:41:48+00:00^* model_count 43^* fields slug^* name^* developer^* model_type^* modality^* parameters^* context_window^* max_output^* open_weights^* license^* release_date^* input_price^* output_price^* price_unit^* price_tiers^* vram_q4^* vram_q4_gb^* min_gpu^* intelligence^* api_providers^* official_url^* retired^* convly_url^* developer Google^* price_unit Not reported^* price_tiers Not reported^* Specifications 2 · 42 fields cache creation input token cost above 200k tokens 2.5e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost 1.25e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost above 200k tokens 2.5e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost above 200k tokens priority 4.5e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost flex 1.25e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* cache read input token cost priority 2.25e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* deprecation date 2026-10-20^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* google maps grounding cost per query 0.025^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token 1.25e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token above 200k tokens 2.5e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token above 200k tokens priority 4.5e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token batches 6.25e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token flex 6.25e-7^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* input cost per token priority 2.25e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* litellm provider vertex_ai-language-models^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* max input tokens 1,048,576^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* max output tokens 65,535^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* max tokens 65,535^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* mode chat^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token 1.0e-5^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token above 200k tokens 1.5e-5^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token above 200k tokens priority 2.7e-5^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token batches 5.0e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token flex 5.0e-6^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* output cost per token priority 1.8e-5^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* prompt cache min tokens 2,048^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* search context cost per query search_context_size_low 0.035^* search_context_size_medium 0.035^* search_context_size_high 0.035^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* search free requests count 10,000^* period day^* shared_group gemini-2.5-pro^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supported endpoints /v1/chat/completions^* /v1/completions^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supported modalities text^* image^* audio^* video^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supported output modalities text^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports audio input Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports function calling Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports pdf input Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports prompt caching Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports reasoning Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports response schema Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports system messages Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports tool choice Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports video input Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports vision Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^* supports web search Yes^* Scope and conditions native_context provider vertex_ai-language-models^* mode chat^* full_native_model_id gemini-2.5-pro^* pricing_scope Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*
Input modalities	text image audio video pdf	text image audio video pdf
Output modalities	text	text

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Gemini 2.5 Flash

Provider offer

Gemini 2.5 Pro

Provider offer

Gemini 2.5 Flash / Pricing tiers 2

Provider / scope	Rate	Currency	Amount / unit
GoogleGemini 2.5 FlashStandard audio	Cached input	USD	0.1 / 1M tokens
	Input	USD	1 / 1M tokens
	Output	USD	2.5 / 1M tokens
GoogleGemini 2.5 FlashStandard text/image/video	Cached input	USD	0.03 / 1M tokens
	Input	USD	0.3 / 1M tokens
	Output	USD	2.5 / 1M tokens

Gemini 2.5 Pro / Pricing tiers 6

Provider / scope	Rate	Currency	Amount / unit
GoogleGemini 2.5 ProStandard Token tier: 0 – 200,000	Cached input	USD	0.125 / 1M tokens
	Input	USD	1.25 / 1M tokens
	Output	USD	10 / 1M tokens
GoogleGemini 2.5 ProStandard Token tier: 200,000 – No stated upper limit	Cached input	USD	0.25 / 1M tokens
	Input	USD	2.5 / 1M tokens
	Output	USD	15 / 1M tokens
Google Vertex AIGemini 2.5 ProBatch Token tier: 0 – 200,000	Input	USD	0.625 / 1M tokens
	Output	USD	5 / 1M tokens
Google Vertex AIGemini 2.5 ProBatch Token tier: 200,000 – No stated upper limit	Input	USD	1.25 / 1M tokens
	Output	USD	7.5 / 1M tokens
Google Vertex AIGemini 2.5 ProStandard Token tier: 0 – 200,000	Cached input	USD	0.125 / 1M tokens
	Input	USD	1.25 / 1M tokens
	Output	USD	10 / 1M tokens
Google Vertex AIGemini 2.5 ProStandard Token tier: 200,000 – No stated upper limit	Cached input	USD	0.25 / 1M tokens
	Input	USD	2.5 / 1M tokens
	Output	USD	15 / 1M tokens

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Test version

Arena text preference / chinesehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,449.46 rating

Confidence interval: 1,442.90 – 1,456.03

9165 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,507.10 rating

Confidence interval: 1,500.44 – 1,513.76

9313 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,423.43 rating

Confidence interval: 1,419.23 – 1,427.62

26352 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,451.46 rating

Confidence interval: 1,447.26 – 1,455.65

26935 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,399.87 rating

Confidence interval: 1,394.93 – 1,404.81

17646 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,453.75 rating

Confidence interval: 1,448.69 – 1,458.82

17680 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,417.78 rating

Confidence interval: 1,414.53 – 1,421.03

54665 votes

Oct 28, 2026

Category: english
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,458.07 rating

Confidence interval: 1,454.77 – 1,461.38

54037 votes

Oct 28, 2026

Category: english
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,404.04 rating

Confidence interval: 1,400.72 – 1,407.36

90056 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,460.40 rating

Confidence interval: 1,457.03 – 1,463.77

91417 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,426.01 rating

Confidence interval: 1,419.37 – 1,432.65

8404 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,451.91 rating

Confidence interval: 1,445.17 – 1,458.66

8323 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,432.09 rating

Confidence interval: 1,419.51 – 1,444.68

2609 votes

Oct 28, 2026

Category: french
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,473.12 rating

Confidence interval: 1,459.86 – 1,486.37

2389 votes

Oct 28, 2026

Category: french
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,417.58 rating

Confidence interval: 1,405.65 – 1,429.52

2686 votes

Oct 28, 2026

Category: german
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,487.06 rating

Confidence interval: 1,474.55 – 1,499.58

2652 votes

Oct 28, 2026

Category: german
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,422.03 rating

Confidence interval: 1,418.94 – 1,425.11

65107 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,454.73 rating

Confidence interval: 1,451.62 – 1,457.83

65896 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,420.38 rating

Confidence interval: 1,416.32 – 1,424.44

28888 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,452.54 rating

Confidence interval: 1,448.46 – 1,456.63

28959 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,403.48 rating

Confidence interval: 1,399.01 – 1,407.95

22738 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,439.47 rating

Confidence interval: 1,434.94 – 1,443.99

22809 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,393.42 rating

Confidence interval: 1,389.02 – 1,397.82

23176 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,441.23 rating

Confidence interval: 1,436.70 – 1,445.75

23305 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,430.52 rating

Confidence interval: 1,423.97 – 1,437.07

8906 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,480.26 rating

Confidence interval: 1,473.56 – 1,486.96

8933 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,432.66 rating

Confidence interval: 1,428.04 – 1,437.28

20587 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,480.06 rating

Confidence interval: 1,475.43 – 1,484.70

20864 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,422.40 rating

Confidence interval: 1,415.25 – 1,429.54

7071 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,454.37 rating

Confidence interval: 1,447.03 – 1,461.71

6914 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,427.53 rating

Confidence interval: 1,420.51 – 1,434.55

7887 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,475.96 rating

Confidence interval: 1,468.83 – 1,483.09

7987 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,425.06 rating

Confidence interval: 1,421.54 – 1,428.58

43830 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,458.99 rating

Confidence interval: 1,455.44 – 1,462.54

44018 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,405.33 rating

Confidence interval: 1,401.23 – 1,409.42

28432 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,453.86 rating

Confidence interval: 1,449.64 – 1,458.08

28255 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,404.88 rating

Confidence interval: 1,401.12 – 1,408.64

34820 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,436.58 rating

Confidence interval: 1,432.76 – 1,440.40

35203 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,396.12 rating

Confidence interval: 1,382.14 – 1,410.11

2043 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,461.15 rating

Confidence interval: 1,446.52 – 1,475.78

2065 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,384.66 rating

Confidence interval: 1,371.46 – 1,397.85

2368 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,434.38 rating

Confidence interval: 1,421.42 – 1,447.33

2501 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,418.81 rating

Confidence interval: 1,414.91 – 1,422.71

33302 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,449.08 rating

Confidence interval: 1,445.16 – 1,452.99

34004 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,410.67 rating

Confidence interval: 1,404.02 – 1,417.31

8000 votes

Oct 28, 2026

Category: math
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,449.68 rating

Confidence interval: 1,442.81 – 1,456.55

7814 votes

Oct 28, 2026

Category: math
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,407.93 rating

Confidence interval: 1,403.37 – 1,412.49

21701 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,452.55 rating

Confidence interval: 1,447.87 – 1,457.22

21182 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,409.19 rating

Confidence interval: 1,406.20 – 1,412.18

70734 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,451.44 rating

Confidence interval: 1,448.39 – 1,454.49

71214 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,416.91 rating

Confidence interval: 1,414.51 – 1,419.31

125457 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,457.70 rating

Confidence interval: 1,455.27 – 1,460.14

125307 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,413.14 rating

Confidence interval: 1,404.88 – 1,421.41

6189 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,478.94 rating

Confidence interval: 1,470.54 – 1,487.34

6493 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,414.92 rating

Confidence interval: 1,409.41 – 1,420.44

12296 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,460.68 rating

Confidence interval: 1,455.05 – 1,466.31

12203 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash

1,421.67 rating

Confidence interval: 1,410.77 – 1,432.58

3460 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Gemini 2.5 Flash
Evaluation type: human preference

Gemini 2.5 Pro

1,473.61 rating

Confidence interval: 1,462.62 – 1,484.59

3455 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Gemini 2.5 Pro
Evaluation type: human preference

Arena text preference / chinesehuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,449.67 rating

Confidence interval: 1,443.10 – 1,456.23

9167 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,507.42 rating

Confidence interval: 1,500.76 – 1,514.08

9318 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,423.52 rating

Confidence interval: 1,419.33 – 1,427.72

26379 votes

Oct 15, 2026

Category: coding
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,451.58 rating

Confidence interval: 1,447.38 – 1,455.78

26964 votes

Oct 15, 2026

Category: coding
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,399.91 rating

Confidence interval: 1,394.97 – 1,404.85

17664 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,453.63 rating

Confidence interval: 1,448.57 – 1,458.70

17694 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,417.73 rating

Confidence interval: 1,414.48 – 1,420.98

54705 votes

Oct 15, 2026

Category: english
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,458.10 rating

Confidence interval: 1,454.79 – 1,461.40

54059 votes

Oct 15, 2026

Category: english
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,404.06 rating

Confidence interval: 1,400.74 – 1,407.37

90112 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,460.46 rating

Confidence interval: 1,457.09 – 1,463.83

91459 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,425.84 rating

Confidence interval: 1,419.19 – 1,432.48

8407 votes

Oct 15, 2026

Category: expert
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,452.08 rating

Confidence interval: 1,445.33 – 1,458.82

8327 votes

Oct 15, 2026

Category: expert
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,432.00 rating

Confidence interval: 1,419.41 – 1,444.60

2617 votes

Oct 15, 2026

Category: french
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,472.38 rating

Confidence interval: 1,459.10 – 1,485.66

2391 votes

Oct 15, 2026

Category: french
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,417.27 rating

Confidence interval: 1,405.32 – 1,429.22

2686 votes

Oct 15, 2026

Category: german
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,487.13 rating

Confidence interval: 1,474.60 – 1,499.66

2652 votes

Oct 15, 2026

Category: german
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,422.11 rating

Confidence interval: 1,419.03 – 1,425.20

65147 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,454.75 rating

Confidence interval: 1,451.65 – 1,457.86

65927 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,420.24 rating

Confidence interval: 1,416.18 – 1,424.30

28916 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,452.53 rating

Confidence interval: 1,448.44 – 1,456.61

28963 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,403.52 rating

Confidence interval: 1,399.05 – 1,407.99

22747 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,439.51 rating

Confidence interval: 1,434.98 – 1,444.04

22814 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,393.41 rating

Confidence interval: 1,389.01 – 1,397.81

23191 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,441.09 rating

Confidence interval: 1,436.57 – 1,445.61

23329 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,430.10 rating

Confidence interval: 1,423.55 – 1,436.65

8909 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,479.68 rating

Confidence interval: 1,472.98 – 1,486.38

8937 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,432.81 rating

Confidence interval: 1,428.18 – 1,437.43

20582 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,480.05 rating

Confidence interval: 1,475.42 – 1,484.69

20874 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,422.36 rating

Confidence interval: 1,415.21 – 1,429.50

7072 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,454.44 rating

Confidence interval: 1,447.10 – 1,461.78

6918 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,427.89 rating

Confidence interval: 1,420.87 – 1,434.91

7893 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,475.79 rating

Confidence interval: 1,468.66 – 1,482.92

7994 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,425.08 rating

Confidence interval: 1,421.56 – 1,428.60

43860 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,459.11 rating

Confidence interval: 1,455.56 – 1,462.66

44050 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,405.37 rating

Confidence interval: 1,401.27 – 1,409.47

28446 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,453.80 rating

Confidence interval: 1,449.58 – 1,458.02

28272 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,404.96 rating

Confidence interval: 1,401.19 – 1,408.72

34837 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,436.49 rating

Confidence interval: 1,432.67 – 1,440.31

35220 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,396.41 rating

Confidence interval: 1,382.43 – 1,410.39

2044 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,460.58 rating

Confidence interval: 1,445.94 – 1,475.21

2061 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,385.13 rating

Confidence interval: 1,371.94 – 1,398.31

2376 votes

Oct 15, 2026

Category: korean
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,434.72 rating

Confidence interval: 1,421.75 – 1,447.69

2499 votes

Oct 15, 2026

Category: korean
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,418.89 rating

Confidence interval: 1,414.98 – 1,422.79

33331 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,449.14 rating

Confidence interval: 1,445.23 – 1,453.06

34031 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,410.62 rating

Confidence interval: 1,403.97 – 1,417.27

8004 votes

Oct 15, 2026

Category: math
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,449.77 rating

Confidence interval: 1,442.90 – 1,456.64

7817 votes

Oct 15, 2026

Category: math
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,407.90 rating

Confidence interval: 1,403.34 – 1,412.47

21709 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,452.63 rating

Confidence interval: 1,447.96 – 1,457.30

21195 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,409.28 rating

Confidence interval: 1,406.29 – 1,412.27

70758 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,451.50 rating

Confidence interval: 1,448.45 – 1,454.55

71251 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,416.89 rating

Confidence interval: 1,414.49 – 1,419.29

125521 votes

Oct 15, 2026

Category: overall
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,457.73 rating

Confidence interval: 1,455.29 – 1,460.16

125366 votes

Oct 15, 2026

Category: overall
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,413.08 rating

Confidence interval: 1,404.81 – 1,421.34

6189 votes

Oct 15, 2026

Category: polish
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,478.84 rating

Confidence interval: 1,470.44 – 1,487.25

6495 votes

Oct 15, 2026

Category: polish
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,414.70 rating

Confidence interval: 1,409.18 – 1,420.22

12290 votes

Oct 15, 2026

Category: russian
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,460.42 rating

Confidence interval: 1,454.79 – 1,466.04

12211 votes

Oct 15, 2026

Category: russian
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

Gemini 2.5 Flash

1,421.26 rating

Confidence interval: 1,410.32 – 1,432.20

3454 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: gemini-2.5-flash
Evaluation type: human preference

Gemini 2.5 Pro

1,473.47 rating

Confidence interval: 1,462.46 – 1,484.49

3451 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: gemini-2.5-pro
Evaluation type: human preference

* Provisional data