RankingDeepSWE 1.1 · 1.1

DeepSWE 1.1 · 1.1

Data updated 12 Sept 2026

Bucket
Coding
Unit
percent
Direction
Higher is better
Version
1.1
Display harness
Qwen/Qwen3.8-2.4T-A95B
Board
https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B

Compare published benchmark results with category weights →

Models

ModelScoreHarnessEvidenceSource-recorded date
GPT-5.6 SolOpenAI73%
Reported settings & source

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Best of Claude Code and mini-SWE-agent; Qwen best Claude Code; temp1,top_p.95,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: DeepSWE 1.1 · reviewed 2026-09-12

Qwen/Qwen3.8-2.4T-A95Blab self-report2026-09-12
Claude Fable 5Anthropic70%
Reported settings & source

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Best of Claude Code and mini-SWE-agent; Qwen best Claude Code; temp1,top_p.95,256K.

First-party reported result.

Comparison limit: The source states that Fable 5 results may involve fallback execution; an exact configuration is not established.

Qwen/Qwen3.8-2.4T-A95B · Performance table: DeepSWE 1.1 · reviewed 2026-09-12

Qwen/Qwen3.8-2.4T-A95Blab self-report2026-09-12
Claude Opus 4.8Anthropic59%
Reported settings & source

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Best of Claude Code and mini-SWE-agent; Qwen best Claude Code; temp1,top_p.95,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: DeepSWE 1.1 · reviewed 2026-09-12

Qwen/Qwen3.8-2.4T-A95Blab self-report2026-09-12
Qwen 3.8-MaxQwen56.6%
Reported settings & source

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Best of Claude Code and mini-SWE-agent; Qwen best Claude Code; temp1,top_p.95,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: DeepSWE 1.1 · reviewed 2026-09-12

Qwen/Qwen3.8-2.4T-A95Blab self-report2026-09-12
Qwen3.7-maxQwen21.6%
Reported settings & source

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Best of Claude Code and mini-SWE-agent; Qwen best Claude Code; temp1,top_p.95,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: DeepSWE 1.1 · reviewed 2026-09-12

Qwen/Qwen3.8-2.4T-A95Blab self-report2026-09-12