Codesota · Models · o4-miniOpenAI16 results · 16 benchmarks
Model card

o4-mini.

OpenAIproprietary2 current SOTA
§ 02 · Benchmarks

Every benchmark o4-mini has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01HumanEvalComputer Code · Code Generationpass@197.3%#1/42—source ↗
02MBPPComputer Code · Code Generationpass@194.9%#1/19—source ↗
03AIME 2024Reasoning · Mathematical Reasoningaccuracy93.4%#2/11—source ↗
04ARC-AGI-1Reasoning · Logical Reasoningaccuracy79.0%#3/5—source ↗
05ARC-AGI-2Reasoning · Logical Reasoningaccuracy3.0%#3/3—source ↗
06ARC-ChallengeReasoning · Commonsense Reasoningaccuracy97.3%#4/10—source ↗
07GSM8KReasoning · Mathematical Reasoningaccuracy99.0%#4/48—source ↗
08LiveCodeBench ProComputer Code · Code Generationelo2092.00#4/10—source ↗
09MATHReasoning · Mathematical Reasoningaccuracy97.5%#5/46—source ↗
10LiveCodeBenchComputer Code · Code Generationpass@172.8%#7/302024-03-12source ↗
11AIME 2025Reasoning · Mathematical Reasoningaccuracy92.7%#8/22—source ↗
12MMLUReasoning · Commonsense Reasoningaccuracy90.0%#15/642025-04-16source ↗
13SWE-Bench VerifiedComputer Code · Code Generationresolve-rate68.1%#22/39—source ↗
14GPQA DiamondReasoning · Multi-step Reasoningaccuracy77.6%#34/74—source ↗
15HLEReasoning · Multi-step Reasoningaccuracy18.1%#42/74—source ↗
16SWE-bench VerifiedAgentic AI · SWE-benchresolve-rate68.1%#45/81—source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where o4-mini actually performs.

Computer Code
5
benchmarks
avg rank #7.0 · 2 SOTA
Reasoning
10
benchmarks
avg rank #12.0
Agentic AI
1
benchmark
avg rank #45.0
§ 04 · Papers

1 paper with results for o4-mini.

  1. 2024-03-12· Computer Code· 1 result

    LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

§ 05 · Related models

Other OpenAI models scored on Codesota.

GPT-4o
Undisclosed params · 38 results · 9 SOTA
o3
17 results · 5 SOTA
o3 (high)
2 results · 1 SOTA
Codex / GPT-5.5
1 result · 1 SOTA
Codex CLI (GPT-5.5)
1 result · 1 SOTA
o4-mini (high)
1 result · 1 SOTA
o1
12 results
GPT-4.1
8 results
§ 06 · Sources & freshness

Where these numbers come from.

openai-simple-evals
6
results
openai-system-card
2
results
arcprize-leaderboard
2
results
official-model-card
1
result
livecodebench-pro-official
1
result
official-leaderboard
1
result
swebench-leaderboard
1
result
scale-hle-official
1
result
editorial
1
result
12 of 16 rows marked verified. · first result 2024-03-12, latest 2025-04-16.