OpenAI: o3-mini
10 benchmarks
Leaderboard position
#384
Overall rank (of 1124 models)
1348
Elo rating
10
Benchmarks
Top 34.2%
Percentile
In OpenAI (of 74 models)
Above: Z.ai: glm-4.7-flash #383
Below: Amazon: nova-2.0-sonic #385
Benchmark highlights
Best benchmark
MATH
97.9
Worst benchmark
Humanity's Last Exam (no tools)
9
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 10 benchmarks
1/10
10.0%
1/10
10.0%
1/10
10.0%
1/10
10.0%
1/10
10.0%
1/10
10.0%
1/10
10.0%
1/10
10.0%
| Model | Votes | % of benchmarks |
|---|---|---|
| Nex AGI: Nex-N2 Pro | 1 | 10.0% |
| Technology Innovation Institute: falcon-h1r-7b | 1 | 10.0% |
| OpenBMB: minicpm5-2b | 1 | 10.0% |
| NVIDIA Corporation: nvidia-nemotron-3.5-lightning-30b-a3b-bf16 | 1 | 10.0% |
| recursiveai: ripple-65b-preview | 1 | 10.0% |
| upstage: solar-pro-3 | 1 | 10.0% |
| DeepSeek: deepseek-v3 | 1 | 10.0% |
| Mistral AI: ministral-3-14b-instruct-2512 | 1 | 10.0% |
| Google: Gemini 3.1 Pro Preview | 1 | 10.0% |
| China Mobile: jt-mini | 1 | 10.0% |
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.