Nanbeige4.1-3B — benchmark results
Nanbeige Lab's 3B reasoning and agentic model, an SFT+RL post-train of its Nanbeige4-3B base aimed at matching much larger Qwen3 models (February 2026). Provider: Nanbeige. Released 2026-02-11. Access: Open.
Unified ELO 1452 ± 34, rank #986 of 1776 rated models, from 42 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GPQA Diamond | 84.95 | Accuracy (%) | 83.9 |
| OpenEvals - GPQA Diamond | 83.8 | Accuracy (%) | 65.4 |
| AA Humanity's Last Exam | 10.01 | Accuracy (%) | 61.8 |
| AA Omniscience | -41.93 | Score | 50.9 |
| Artificial Analysis Intelligence Index | 11.09 | Intelligence Index | 38.4 |
| AA SciCode | 26.6 | Accuracy (%) | 33 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| AA IFBench | 35.44 | Accuracy (%) | 27.5 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| AA Omniscience - Science, Engineering & Mathematics | 19 | Accuracy (%) | 26.3 |
| AA Omniscience - Software Engineering (SWE) - Julia | 4 | Accuracy (%) | 23.7 |
| AA TAU-2 Bench | 21.64 | Accuracy (%) | 22.3 |
Interactive version: theaggregate.ai/model?slug=nanbeige4-1-3b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.