GeekRadar / The comparison desk

COMPARE.

AI models

google

Gemini 3.1 Pro Preview

AI model Released Feb 19, 2026

API mode: Chat^*
Context window: 1,048,576 tokens
Maximum output: 65,536 tokens
Open weights: No

Capability & preference

Human preference · Arena

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

Gemini 3.1 Pro Preview 1480.1 Gemini 3.1 Pro Preview · 95% interval 1477.2–1483.0 · 132,547 votes · 2026-10-28

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Gemini 3.1 Pro Preview

Tested configuration Radar task score

Unrated

3/4 core tests · not enough evidence

6 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Gemini 3.1 Pro Preview 94.4^*% Approx. 95% interval: 91.2–97.6% · 2026-08-06

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Gemini 3.1 Pro Preview 34.0^*% Approx. 95% interval: 24.7–43.3% · 2026-07-27

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Gemini 3.1 Pro Preview Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Gemini 3.1 Pro Preview 73.5^*% Approx. 95% interval: 70.8–76.2% · 2026-08-10

End-to-end software

MirrorCode · Separate result

Whole-program reimplementation with hidden tests; ML + Private, two languages. Budget: seven days and ten billion tokens per attempt.

Gemini 3.1 Pro Preview 8.9^*% Approx. 95% interval: 0.0–17.8% · 2026-08-10

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Gemini 3.1 Pro Preview 95.6^*% Approx. 95% interval: 89.5–100.0% · 2026-08-06

Visual spatial reasoning

Furniture Assembly · Separate result

Assembly-error detection from photos and manuals, with zoom and Python tools. Uses model-assisted grading; not a general vision score.

Gemini 3.1 Pro Preview 26.7^*% Approx. 95% interval: 15.6–37.7% · 2026-09-10

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

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.

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

Gemini 3.1 Pro Preview

1,528.23 rating

Confidence interval: 1,521.10 – 1,535.36

9208 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,483.51 rating

Confidence interval: 1,479.02 – 1,487.99

36254 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,482.33 rating

Confidence interval: 1,477.11 – 1,487.55

24631 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,478.08 rating

Confidence interval: 1,474.22 – 1,481.94

57933 votes

Oct 28, 2026

Category: english
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,489.80 rating

Confidence interval: 1,485.91 – 1,493.68

99574 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,483.92 rating

Confidence interval: 1,477.81 – 1,490.03

13782 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,487.94 rating

Confidence interval: 1,476.94 – 1,498.95

4387 votes

Oct 28, 2026

Category: french
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,490.80 rating

Confidence interval: 1,476.69 – 1,504.90

2198 votes

Oct 28, 2026

Category: german
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,484.56 rating

Confidence interval: 1,481.04 – 1,488.09

86065 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,480.01 rating

Confidence interval: 1,475.56 – 1,484.46

38454 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,459.17 rating

Confidence interval: 1,454.26 – 1,464.07

25607 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,465.59 rating

Confidence interval: 1,460.74 – 1,470.44

30803 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,486.29 rating

Confidence interval: 1,479.63 – 1,492.95

10871 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,496.82 rating

Confidence interval: 1,491.72 – 1,501.91

22070 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,478.40 rating

Confidence interval: 1,470.63 – 1,486.17

7499 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,485.75 rating

Confidence interval: 1,478.72 – 1,492.77

9860 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,486.56 rating

Confidence interval: 1,482.57 – 1,490.56

51951 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,481.38 rating

Confidence interval: 1,476.76 – 1,485.99

33991 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,466.04 rating

Confidence interval: 1,461.84 – 1,470.23

45417 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,492.95 rating

Confidence interval: 1,476.16 – 1,509.74

1656 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,455.46 rating

Confidence interval: 1,441.37 – 1,469.55

2340 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,482.06 rating

Confidence interval: 1,477.97 – 1,486.15

58532 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,485.31 rating

Confidence interval: 1,477.49 – 1,493.14

6932 votes

Oct 28, 2026

Category: math
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,486.26 rating

Confidence interval: 1,481.08 – 1,491.45

22386 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,476.30 rating

Confidence interval: 1,472.72 – 1,479.87

74599 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,480.11 rating

Confidence interval: 1,477.20 – 1,483.01

132547 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,496.93 rating

Confidence interval: 1,484.71 – 1,509.16

2516 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,496.67 rating

Confidence interval: 1,490.87 – 1,502.46

15237 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

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

Gemini 3.1 Pro Preview

1,479.47 rating

Confidence interval: 1,469.02 – 1,489.91

4256 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Gemini 3.1 Pro Preview
Evaluation type: human preference

Run it locally

Inference · memory estimate

Gemini 3.1 Pro Preview

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

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 3.1 Pro Preview

Provider offer

Capabilities

Context window: 1,048,576 tokens
Maximum input: 1,048,576 tokens^*
Maximum output: 65,536 tokens
Reasoning: Yes
Tool calling: Yes
Structured output: Yes^*
Open weights: No
Knowledge cutoff: 2025-01
API mode: Chat^*
Image input: Yes^*
PDF input: Yes^*
Video input: Yes^*
Audio input: Yes^*
Prompt caching: Yes^*
System messages: Yes^*
Tool choice: Yes^*
Web search: Yes^*
Model license: Proprietary

Input modalities

text
image
video
audio
pdf

Output modalities

text

System configuration

Detailed specifications

Specifications · 44 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-3.1-pro-preview^*
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

2.0e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

4.0e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

7.2e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

3.6e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

0.014^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

2.0e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

4.0e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

7.2e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

1.0e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

1.0e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

3.6e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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

65,536^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

65,536^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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-3.1-pro-preview^*
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 image

0.00012^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

1.2e-5^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

1.8e-5^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

3.24e-5^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

6.0e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

6.0e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

2.16e-5^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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

4,096.0^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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: 0.014^*
search_context_size_medium: 0.014^*
search_context_size_high: 0.014^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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: 5,000^*
period: month^*
shared_group: gemini-3^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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 native streaming

Yes^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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-3.1-pro-preview^*
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.^*

web search billing unit

per_query^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.1-pro-preview^*
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.^*

* Provisional data

Capability & preference

Human preference · Arena

Model performance

Gemini 3.1 Pro Preview

Scientific reasoning

Novel problem solving

Advanced mathematics

Factual answers

End-to-end software

Competition mathematics

Research mathematics

Visual spatial reasoning

Recorded results

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview

Run it locally

Gemini 3.1 Pro Preview

API cost

Gemini 3.1 Pro Preview

Capabilities

Input modalities

Output modalities

System configuration

Detailed specifications