OpenAI: sora
1 benchmarks
Leaderboard position
#687
Overall rank (of 1121 models)
691
Elo rating
1
Benchmarks
Top 61.3%
Percentile
In OpenAI (of 74 models)
Above: DeepSeek: deepseek-ocr #686
Below: Stability AI: stable-diffusion-xl-1.0 #688
Benchmark highlights
Best benchmark
Text-to-Video Arena (Snapshot from 20 june 2026)
1070
Worst benchmark
Text-to-Video Arena (Snapshot from 20 june 2026)
1070
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 1 benchmarks
1/1
100.0%
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| MATH-500 | ~83.55 | 50% | — |
| AIME 2025 | ~60.74 | 50% | — |
| AIME 2026 | ~70.33 | 50% | — |
| HMMT Feb 2026 | ~61.83 | 50% | — |
| GPQA Diamond | ~54.49 | 50% | — |
| MMLU-Pro | ~57.21 | 50% | — |
| Humanity's Last Exam (no tools) | ~8.73 | 50% | — |
| IFEval | ~80.04 | 50% | — |
| IFBench | ~50.63 | 50% | — |
| HumanEval | ~68.96 | 50% | — |
| MBPP | ~70.82 | 50% | — |
| Terminal-Bench v2.1 | ~15.84 | 50% | — |
| MMLU | ~63.46 | 50% | — |
| SWE-bench Verified | ~34.07 | 50% | — |
| SWE-bench Pro | ~13.35 | 50% | — |
| SciCode | ~24.37 | 50% | — |
| AA-LCR | ~39.9 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.97 | 50% | — |
| GSM8K | ~76.67 | 50% | — |
| -(CoderPPL) | ~-1.94 | 50% | — |
| LiveCodeBench v6 | ~52.2 | 50% | — |
| MMMU-Pro | ~49.88 | 50% | — |
| MATH | ~53.9 | 50% | — |
| BBH | ~61.7 | 50% | — |