Benchmark Almanac

QwenSWEBench

Claude Fable 5 86.3% leads since June 2026
Claude Fable 5 86.3% leads since June 2026
In use

Qwen in-house software-engineering benchmark run in Claude Code (avg@3, 8-hour limit). Task and scoring details unpublished.

Lab-created in-house eval (Alibaba Qwen).

Made by
Alibaba Qwen
Kind
Fixing real repositories
Level
Expert
Scored
Checked automatically
Answers
Code
Tasks
Kept private
Strongest model tested
Claude Fable 5 #11 on the capability index
Last in a launch post
August 2026
Last model added
August 2026
Scores refreshed
November 12th, 2026
5
Models scored on its own leaderboard
2
Launch posts list it, from 1 lab

Claude Fable 5 leads with 86.3% among models released by August 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

Claude Fable 5 leads with 86.3%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 86.3 Claude Fable 5
  2. 84.0 Claude Opus 4.8
  3. 80.7 Qwen 3.8 Max
  4. 73.5 GPT-5.6 Sol
  5. 63.4 Qwen3.7-Max
  1. 1 Claude Fable 5 86.3%
  2. 2 Claude Opus 4.8 84%
  3. 3 Qwen 3.8 Max 80.7%
  4. 4 GPT-5.6 Sol max 73.5%
  5. 5 Qwen3.7-Max 63.4%

Source: Official QwenSWEBench leaderboard

Sources: Official QwenSWEBench leaderboard and labs’ model cards

#ModelScoreSettingDateSource
1 Claude Fable 5 86.3% Jun 2026 Official leaderboard
2 Claude Opus 4.8 84% May 2026 Official leaderboard
3 Qwen 3.8 Max 80.7% Aug 2026 Official leaderboard
4 GPT-5.6 Sol 73.5% max Jul 2026 Official leaderboard
5 Qwen3.7-Max 63.4% May 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5 86.3% Jun 2026 Official leaderboard
2 Claude Opus 4.8 84% May 2026 Official leaderboard
3 Qwen 3.8 Max 80.7% Aug 2026 Official leaderboard
4 Qwen 3.8 27B 79% Aug 2026 Lab model card
5 GPT-5.6 Sol 73.5% max Jul 2026 Official leaderboard
6 Qwen3.7-Max 63.4% May 2026 Official leaderboard

Labs report scores for 2 models in their cards. Switch the scores above to rank them together.

3 models have held number one on the official leaderboard since 2023 3 models have held number one with claims included since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen Anthropic
Own leaderboard Passed 85% in Jun 2026, by Claude Fable 5
Claude Fable 5 86.3%

Source: Official QwenSWEBench leaderboard

Claude Fable 5 on the official leaderboard passed 85% in June 2026

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 Qwen3.7-Max 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 Qwen3.7-Max

Sources: Official QwenSWEBench leaderboard and labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Qwen
DateLaunch postScoreAs the post writes it
Aug 14, 2026 Qwen 3.8 27B 79 Software engineering QwenSWEBench (avg@3)
Aug 3, 2026 Qwen 3.8 Max 80.7 QwenSWEBench

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Qwen 3.8 Max 80.7% QwenSWEBench 80.7% Leaderboard Same

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471