Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

OpenAI: o3-mini

10 benchmarks
CompanyOpenAI
Country of originUSA

Leaderboard position

#387
Overall rank (of 1126 models)
1351
Elo rating
10
Benchmarks
Top 34.4%
Percentile
In OpenAI (of 74 models)

Benchmark highlights

Nearest competitor from another company

The model from another company with the most similar benchmark scores.

appeared as nearest in 1 of 10 benchmarks

Benchmarks

Predicted scores

Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.

Benchmark Predicted Confidence Based on
AIME 2025 ~81.83 63% OpenAI: gpt-oss-20b, webai-official: twil-8b, LLM360: k2-think-v2
IFBench ~62.93 63% webai-official: twil-8b, LiquidAI: lfm-2.5-24b-a2b, xhtoken: spark-x2.5-4b
AIME 2026 ~82.82 62% webai-official: twil-8b, xhtoken: spark-x2.5-4b, xhtoken: spark-x2.6-4b
HMMT Feb 2026 ~74.22 62% webai-official: twil-8b, xhtoken: spark-x2.5-4b, xhtoken: spark-x2.6-4b
SWE-bench Verified ~54.95 62% Cohere Labs: north-mini-code-1.0, OpenAI: gpt-oss-20b, LiquidAI: lfm-2.5-24b-a2b
SWE-bench Pro ~32.85 62% Cohere Labs: north-mini-code-1.0, xhtoken: spark-x2.5-4b, xhtoken: spark-x2.6-4b
AA-LCR ~53.29 62% xhtoken: spark-x2.5-4b, NVIDIA Corporation: nvidia-nemotron-3.5-lightning-30b-a3b-bf16, SpaceXAI: Grok 3
LiveCodeBench v6 ~66.91 62% Cohere Labs: north-mini-code-1.0, OpenAI: gpt-oss-20b, Google: Gemma 4 12B Instruct
MATH-500 ~96.11 61% webai-official: twil-8b, LiquidAI: lfm-2.5-24b-a2b, NVIDIA Corporation: nvidia-nemotron-nano-9b-v2
MMLU-Pro ~74.28 61% webai-official: twil-8b, NVIDIA Corporation: nvidia-nemotron-3.5-lightning-30b-a3b-bf16, Google: Gemma 4 12B Instruct
Terminal-Bench v2.1 ~38.02 61% NVIDIA Corporation: nvidia-nemotron-3.5-lightning-30b-a3b-bf16, LiquidAI: lfm-3-1.7b, inclusionAI: ling-3.0-tiny
Humanity's Last Exam (with tools) ~27.25 61% OpenAI: gpt-oss-20b, xhtoken: spark-x2.6-4b, NVIDIA Corporation: nvidia-nemotron-3-nano-30b-a3b
GSM8K ~99.6 61% OpenAI: gpt-oss-20b, OpenAI: o1, DeepSeek: deepseek-v3
BrowseComp ~52.16 61% xhtoken: spark-x2.5-4b, xhtoken: spark-x2.6-4b, NVIDIA Corporation: nvidia-nemotron-3.5-bolt-74b-a9b-24gb
GPQA ~64.75 61% xhtoken: spark-x2.5-4b, xhtoken: spark-x2.6-4b, NVIDIA Corporation: nvidia-nemotron-3-nano-30b-a3b
Text Arena (Snapshot from 20 june 2026) ~1371.86 61% OpenAI: gpt-oss-20b, OpenAI: gpt-oss-120b, Qwen: qwq-32b
Artificial Analysis Intelligence Index v5.0.1 ~12 60% OpenAI: gpt-6-astra
-(CoderPPL) ~-1.69 60% OpenAI: gpt-oss-20b, Qwen: Qwen3.5 9B, LiquidAI: lfm-3-1.7b
MMMU-Pro ~63.32 60% Google: Gemma 4 12B Instruct, Google: Gemma 4 E4B Instruct, Google: Gemma 4 31B Instruct
Artifical Analysis Intelligence Index v5.0 ~6 60% OpenAI: gpt-6-astra
Artificial Analysis Intelligence Index v4.3.2 ~20.03 60% Qwen: Qwen3.5 9B, inclusionAI: ling-3.0-tiny, Google: Gemma 4 E4B Instruct
CowQA ~83.82 60% OpenAI: GPT-5 Nano, Qwen: Qwen3.5 9B, Google: Gemma 4 E4B Instruct
WikiText-2 (-ppl) ~-7.09 60% OpenAI: gpt-oss-20b, Qwen: Qwen3.5 9B, Google: Gemma 4 E4B Instruct
ARC-Challenge ~79.96 59% Qwen: Qwen3.5 9B, Meta Llama: Llama 3.1 405B Instruct, LiquidAI: lfm-2.5-8b-a1b
HumanEval ~95.9 59% webai-official: twil-8b, Qwen: Qwen3 4B, DeepSeek: deepseek-v2.5