INTELLECT-3 model card (Hugging Face) 26 Nov 2025
INTELLECT-3
INTELLECT-3.
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Prime Intellect Nov 2025
INTELLECT-3
Open weights Flagship
No Epoch Capabilities Index score yet
- MMLU-Pro 81.9% #57 /151
- AIME 2025 88% #61 /143
- LiveCodeBench v6 69.3% #49 /76
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU-Pro | 81.9% | #57 of 151 | Model card | |
| LMArena (Elo) | 1,356 | #170 of 333 | Official leaderboard | |
| Humanity's Last Exam | 14.6% | #117 of 147 | Model card | |
| BullshitBench | 12.7% | #94 of 107 | Official leaderboard | |
| BullshitBench V2 | 7.00% | #114 of 122 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-500 | 98.1% | #6 of 67 | Model card | |
| AIME 2024 | 90.8% | #17 of 87 | Model card | |
| AIME 2025 | 88% | #61 of 143 | Model card | |
| GPQA Diamond | 74.4% | #145 of 284 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v6 | 69.3% | #49 of 76 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 18 | #144 of 183 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 1 of them isn't in the launch post.
INTELLECT-3: Technical Report 18 Dec 2025
Capabilities
- AIME 2024 90.8
- AIME 2025 88
- LiveCodeBench v6 69.3
- GPQA Diamond 74.4
- Humanity's Last Exam 14.6
- MMLU-Pro 81.9