geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
openai

GPT-4o mini

AI model Released

API mode
Chat*
Context window
128,000 tokens
Maximum output
16,384 tokens
Open weights
No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

GPT-4o mini 126.5* GPT-4o mini · 95% interval 120.5–128.6

Human preference · Arena

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

GPT-4o mini 1286.3 gpt-4o-mini-2024-07-18 · 95% interval 1282.8–1289.9 · 68,705 votes · 2026-10-15

Model performance

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

GPT-4o mini

Radar task score

Unrated

Older results · no current score

4 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

GPT-4o mini 37.7*% Approx. 95% interval: 33.0–42.4% · Older result

Novel problem solving

Mystery Game Puzzles · 25%

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

GPT-4o mini 12.0*% Approx. 95% interval: 5.6–18.4%

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

GPT-4o mini 0.7*% Approx. 95% interval: 0.0–1.7%

Factual answers

SimpleQA Verified · 25%

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

GPT-4o mini 8.3*% Approx. 95% interval: 6.6–10.0%

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 · 2026-10-15 · rating

GPT-4o mini

1,264.48 rating

Confidence interval: 1,255.30 – 1,273.67

5778 votes

Category
chinese
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

GPT-4o mini

1,289.47 rating

Confidence interval: 1,282.96 – 1,295.98

10928 votes

Category
coding
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GPT-4o mini

1,267.65 rating

Confidence interval: 1,260.73 – 1,274.57

10486 votes

Category
creative_writing
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

GPT-4o mini

1,300.52 rating

Confidence interval: 1,296.23 – 1,304.81

37735 votes

Category
english
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GPT-4o mini

1,215.90 rating

Confidence interval: 1,210.66 – 1,221.15

43353 votes

Category
exclude_ties
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

GPT-4o mini

1,234.33 rating

Confidence interval: 1,223.57 – 1,245.10

3550 votes

Category
expert
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

GPT-4o mini

1,296.81 rating

Confidence interval: 1,272.27 – 1,321.35

649 votes

Category
french
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

GPT-4o mini

1,272.01 rating

Confidence interval: 1,256.63 – 1,287.39

1641 votes

Category
german
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GPT-4o mini

1,266.84 rating

Confidence interval: 1,261.56 – 1,272.13

18259 votes

Category
hard_prompts
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GPT-4o mini

1,278.30 rating

Confidence interval: 1,271.91 – 1,284.69

11355 votes

Category
hard_prompts_english
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GPT-4o mini

1,264.85 rating

Confidence interval: 1,257.09 – 1,272.62

7765 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GPT-4o mini

1,253.22 rating

Confidence interval: 1,246.71 – 1,259.74

11284 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GPT-4o mini

1,305.07 rating

Confidence interval: 1,294.27 – 1,315.88

3866 votes

Category
industry_legal_and_government
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GPT-4o mini

1,285.95 rating

Confidence interval: 1,279.32 – 1,292.57

11641 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GPT-4o mini

1,271.39 rating

Confidence interval: 1,264.00 – 1,278.78

7966 votes

Category
industry_mathematical
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GPT-4o mini

1,281.67 rating

Confidence interval: 1,270.33 – 1,293.01

3439 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GPT-4o mini

1,290.72 rating

Confidence interval: 1,285.21 – 1,296.24

17795 votes

Category
industry_software_and_it_services
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GPT-4o mini

1,281.96 rating

Confidence interval: 1,276.37 – 1,287.55

18532 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GPT-4o mini

1,258.23 rating

Confidence interval: 1,253.42 – 1,263.05

26707 votes

Category
instruction_following
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

GPT-4o mini

1,215.56 rating

Confidence interval: 1,200.12 – 1,230.99

1793 votes

Category
japanese
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

GPT-4o mini

1,195.23 rating

Confidence interval: 1,174.70 – 1,215.77

1087 votes

Category
korean
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GPT-4o mini

1,288.70 rating

Confidence interval: 1,281.65 – 1,295.74

8989 votes

Category
longer_query
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

GPT-4o mini

1,267.32 rating

Confidence interval: 1,260.31 – 1,274.32

9322 votes

Category
math
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GPT-4o mini

1,285.06 rating

Confidence interval: 1,278.37 – 1,291.75

12279 votes

Category
multi_turn
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GPT-4o mini

1,266.20 rating

Confidence interval: 1,261.65 – 1,270.75

30970 votes

Category
non_english
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

GPT-4o mini

1,286.34 rating

Confidence interval: 1,282.82 – 1,289.86

68705 votes

Category
overall
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

GPT-4o mini

1,244.01 rating

Confidence interval: 1,178.24 – 1,309.78

65 votes

Category
polish
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

GPT-4o mini

1,275.26 rating

Confidence interval: 1,267.81 – 1,282.71

8268 votes

Category
russian
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

GPT-4o mini

1,276.05 rating

Confidence interval: 1,252.28 – 1,299.81

741 votes

Category
spanish
Evaluated configuration
gpt-4o-mini-2024-07-18
Evaluation type
human preference

Run it locally

Inference · memory estimate

GPT-4o mini

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

API cost

USD / month

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

GPT-4o mini

Capabilities

Context window
128,000 tokens
Maximum input
128,000 tokens*
Maximum output
16,384 tokens
Reasoning
No
Tool calling
Yes
Structured output
Yes*
Open weights
No
Knowledge cutoff
2023-09
API mode
Chat*
Image input
Yes*
PDF input
Yes*
Parallel tool calls
Yes*
Prompt caching
Yes*
System messages
Yes*
Tool choice
Yes*
Model license
Proprietary

Input modalities

  • text
  • image
  • pdf

Output modalities

  • text

System configuration

Detailed specifications

Specifications · 22 fields
cache read input token cost
7.5e-8*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
1.25e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
1.5e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
7.5e-8*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
2.5e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
128,000*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
16,384*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
16,384*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
6.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
3.0e-7*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
1.0e-6*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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_high
0.025*
search_context_size_low
0.025*
search_context_size_medium
0.025*
Scope and conditions
native_context
provider
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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
openai*
mode
chat*
full_native_model_id
gpt-4o-mini*
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