BlogLLM Benchmark Scores as Published, Side by Side
QwenQoderBench: Results as Published
Every result the catalog holds for QwenQoderBench: 5 models from 3 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Agentic CodingMaintainer Alibaba Group (Qwen team), internal benchmarkIntroduced 2026Data version 2026103001, as of 2026-10-30
QwenQoderBench is an in-house Qwen benchmark for coding agents, which the Qwen3.8 model card describes as an inhouse benchmark for evaluating user experience on Qoder. The card reports results from Qwen's own testing, and the 2.4T flagship card lists a score of 58.4. The benchmark measures coding-agent tasks, and BenchmarkList reports it as Avg@5.
QwenQoderBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.6 SolOpenAI, released 2026-07-09 | 53.8 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | Effort: max |
| Claude Fable 5Anthropic, released 2026-06-09 | 63.1 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 62.7 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.8-MaxAlibaba, released 2026-08-03 | 58.4 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.7-MaxAlibaba | 36.8 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.