Intern-S1.
Shanghai AI Lab Jul 2025 Open weights Flagship
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.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMU | 77.7% | #15 of 136 | Official leaderboard | |
| XLRS-Bench | 55% | #1 of 4 | Model card | |
| MathVista | 81.5% | #23 of 64 | Model card | |
| MSEarth | 65.7% | #1 of 2 | Model card | |
| MMStar | 74.9% | #17 of 30 | Model card | |
| MicroVQA | 63.9% | #2 of 3 | Model card | |
| MATH-Vision (MathVision) | 62.5% | #31 of 42 | Model card | |
| Scientists' First Exam (SFE) | 44.3% | #5 of 5 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SMolInstruct | 51% | #2 of 2 | Model card | |
| ProteinLMBench | 63.1% | #1 of 1 | Model card |
The benchmarks the lab chose to headline, with the scores it gave.
Every result in the longer documents the lab published with it.