| Benchmark | Model | Rank | Results |
|---|---|---|---|
| agents-on-gaia-text-only-103-validation-tasks | Nanbeige4.1-3B (w/ tools, text-only) | #3 | Accuracy: 69.90 |
| instruction-following-on-arena-hard-auto-v2 | Nanbeige4.1-3B | #3 | Accuracy: 73.2 |
| agents-on-bfclv4 | Nanbeige4.1-3B | #10 | Accuracy: 56.50 |
| instruction-following-on-multichallenge | Nanbeige4.1-3B | #13 | Accuracy: 52.21 |
| code-generation-on-livecodebench-v6 | Nanbeige4.1-3B | #23 | Pass@1: 76.9 |
| agents-on-bench | Nanbeige4.1-3B | #26 | Accuracy: 48.57 |
| deep-research-agents-on-browsecomp | Nanbeige4.1-3B (w/ tools) | #62 | Accuracy: 19.12 |