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

BenchmarkScoreMetricPercentile
OpenEvals - SWE-bench Pro44.3Resolved (%)100
SecCodeBench62.76Total Score88.6
AA TAU-2 Bench79.53Accuracy (%)69.6
AA Omniscience - Software Engineering (SWE) - C44Accuracy (%)61.6
Artificial Analysis Intelligence Index21.11Intelligence Index61.6
Wolfram LLM Benchmarking Project45.9Correct Functionality (%)61.4
SWE-rebench47.8Resolved (%)61.1
AA GPQA Diamond73.74Accuracy (%)59.3
AA Humanity's Last Exam9.31Accuracy (%)59.3
AI Chess Leaderboard (Reasoning)715Elo58.5
AA Omniscience - Software Engineering (SWE) - Python23.5Accuracy (%)57.7
AA Omniscience - Software Engineering (SWE) - Go20Accuracy (%)57.6

Interactive version: theaggregate.ai/model?slug=qwen3-coder-next · How the rankings work · Data refreshed daily, snapshot 2026-07-22.