primeintellect: intellect-3
2 benchmarks
Leaderboard position
#509
Overall rank (of 1121 models)
1068
Elo rating
2
Benchmarks
Top 45.4%
Percentile
In primeintellect (of 1 models)
Above: cloudflare: clef #508
Below: OpenAI: gpt-4o #510
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 2 benchmarks
1/2
50.0%
1/2
50.0%
| Model | Votes | % of benchmarks |
|---|---|---|
| upstage: solar-open-100b | 1 | 50.0% |
| DeepSeek: deepseek-v3-0324 | 1 | 50.0% |
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 | ~90.09 | 50% | — |
| AIME 2025 | ~73.11 | 50% | — |
| AIME 2026 | ~77.63 | 50% | — |
| HMMT Feb 2026 | ~69.15 | 50% | — |
| GPQA Diamond | ~62.78 | 50% | — |
| MMLU-Pro | ~66.46 | 50% | — |
| Humanity's Last Exam (no tools) | ~15.44 | 50% | — |
| IFEval | ~85.19 | 50% | — |
| IFBench | ~56.87 | 50% | — |
| HumanEval | ~79.91 | 50% | — |
| MBPP | ~85.16 | 50% | — |
| Terminal-Bench v2.1 | ~28.91 | 50% | — |
| MMLU | ~73.18 | 50% | — |
| SWE-bench Verified | ~45.89 | 50% | — |
| SWE-bench Pro | ~24.38 | 50% | — |
| SciCode | ~30.26 | 50% | — |
| AA-LCR | ~47.27 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~20.93 | 50% | — |
| GSM8K | ~90.85 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~60.81 | 50% | — |
| MMMU-Pro | ~56.96 | 50% | — |
| MATH | ~69.72 | 50% | — |
| BBH | ~70.07 | 50% | — |