Qwen3 Coder Next — benchmark results
Alibaba's efficiency-focused open Qwen3-Coder-Next agent MoE (80B total, 3B active). Provider: Alibaba. Released 2026-02-03. Access: Open.
Unified ELO 1630 ± 15, rank #411 of 1776 rated models, from 79 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenEvals - SWE-bench Pro | 44.3 | Resolved (%) | 100 |
| SecCodeBench | 62.76 | Total Score | 88.6 |
| AA TAU-2 Bench | 79.53 | Accuracy (%) | 69.6 |
| AA Omniscience - Software Engineering (SWE) - C | 44 | Accuracy (%) | 61.6 |
| Artificial Analysis Intelligence Index | 21.11 | Intelligence Index | 61.6 |
| Wolfram LLM Benchmarking Project | 45.9 | Correct Functionality (%) | 61.4 |
| SWE-rebench | 47.8 | Resolved (%) | 61.1 |
| AA GPQA Diamond | 73.74 | Accuracy (%) | 59.3 |
| AA Humanity's Last Exam | 9.31 | Accuracy (%) | 59.3 |
| AI Chess Leaderboard (Reasoning) | 715 | Elo | 58.5 |
| AA Omniscience - Software Engineering (SWE) - Python | 23.5 | Accuracy (%) | 57.7 |
| AA Omniscience - Software Engineering (SWE) - Go | 20 | Accuracy (%) | 57.6 |
Interactive version: theaggregate.ai/model?slug=qwen3-coder-next · How the rankings work · Data refreshed daily, snapshot 2026-07-22.