Nanbeige4-3B-Thinking-2511 — benchmark results
Chinese Nanbeige Lab's 3B thinking model (November 2025 update), distillation- and RL-trained for outsized function-calling and writing performance. Provider: Nanbeige. Released 2025-11-01. Access: Open.
Unified ELO 1496 ± 44, rank #815 of 1776 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| WritingBench | 79.03 | Score (self-reported) | 80.8 |
| Gorilla API Bench (BFCL) | 51.4 | Overall Accuracy (%) | 73.2 |
| UGI - Willingness (W/10) | 4.5 | W/10 Score | 33.7 |
| UGI Leaderboard | 24.14 | UGI Score | 18.1 |
| Creative Writing v3 | 953.5 | Elo score (self-reported) | 17.8 |
| EQ-Bench Creative Writing v3 | 814.6 | Elo | 17.3 |
| UGI - Natural Intelligence | 13.72 | NatInt Score | 13.6 |
| EQ-Bench Longform Writing | 31.5 | Writing Score (0-100) | 7 |
| EQ-Bench 3 | 1014.3 | Elo | 5.5 |
| EQ-Bench | 672.8 | Normalized Elo (self-reported) | 5.3 |
| UGI - Writing | 9.76 | Writing Score | 1.8 |
Interactive version: theaggregate.ai/model?slug=nanbeige4-3b-thinking-2511 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.