| Benchmark | Model | Rank | Results |
|---|---|---|---|
| science-question-answering-on-frontierscience-olympiad | Agents-A1 | #2 | Accuracy: 79.0 |
| science-question-answering-on-frontierscience-research | Agents-A1 | #2 | Accuracy: 40.0 |
| instruction-following-on-ifbench | Agents-A1 | #4 | Accuracy: 80.6 |
| long-context-understanding-on-longbench-v2 | Agents-A1 | #8 | Accuracy: 60.2 |
| code-generation-on-scicode | Agents-A1 | #9 | Accuracy: 44.3 |
| agents-on-bench | Agents-A1 | #10 | Accuracy: 79.8 |
| deep-research-agents-on-browsecomp | Agents-A1 | #22 | Accuracy: 75.5 |