Qwen 3 Coder Plus: benchmark results
Alibaba's hosted agentic-coding API tier built on Qwen3-Coder 480B A35B MoE, with up to 1M context. Provider: Alibaba. Released 2025-09-23. Access: API.
Unified ELO 1585 ± 1, rank #306 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| WebCoderBench - Performance | 98.54 | Score (%) | 100 |
| SnakeBench | 24.9 | TrueSkill Rating | 64 |
| BenchTable | 51.3 | Total Score (%) | 54.9 |
| MCPMark | 24.8 | Pass@1 (%) | 52.6 |
| BacktestBench | 42.05 | Overall Accuracy (OA) (self-reported) | 45.5 |
| AI Chess Leaderboard (Reasoning) | 639 | Elo | 42.6 |
| WebCoderBench - Functionality Correctness | 54.95 | Score (%) | 30.8 |
| Spider 2.0-Snow | 37.8 | Accuracy (%) | 30 |
| LM Market Cap LMC Score | 40 | LMC Score (0-100) | 27.3 |
| ALE-Bench | 456.5 | Performance (Self-Refine x1) (self-reported) | 21.6 |
| AssertLLM2 | 18.55 | Coverage Formal (self-reported) | 20 |
| FrontierOR | 20 | Sol. quality (self-reported) | 16.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-coder-plus · How It Works · Data refreshed daily, snapshot 2026-09-05.