Benchmark Almanac

SuperCLUE-SWE

Claude Opus 4.8 73.3 leads since May 2026
Not in model cards

Agents complete software engineering tasks in Chinese.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Fixing real repositories
Level
Expert
Scored
Settled by events
Answers
Agent task
Measures
Capability
Language
Chinese
In and out
Text, Code → Actions, Code
Interaction
Agentic
Environment
Terminal
Refresh
One fixed set
Run by
A host
In views
Agents
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
June 2026
Scores refreshed
November 20th, 2026
17
Entries on its own leaderboard, 16 models we track

Claude Opus 4.8 leads with 73.3 among models released by June 2026 Claude Opus 4.8 leads with 73.3 among models released by June 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

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

  1. 1 Claude Opus 4.8 high 73.3
  2. 2 Gemini 3.1 Pro high 66.7
  3. 3 Qwen3.7-Max Thinking 66.7
  4. 4 GLM-5.2 max 63.3
  5. 5 Claude Opus 4.7 high 60.0
  6. 6 Kimi K2.7 Code 56.7
  7. 7 Kimi K2.6 thinking 53.3
  8. 8 DeepSeek-V4-Pro max 53.3
  9. 9 Doubao-Seed-2.0-pro-260215(high) high 50.0
  10. 10 Gemini 3.5 Flash high 50.0
  11. 11 GPT-5.5 high 43.3
  12. 12 GLM-5.1 40.0
  13. 13 Step 3.7 Flash high 40.0
  14. 14 Grok 4.3 36.7
  15. 15 Step 3.5 Flash 33.3
  16. 16 MiMo-V2.5-Pro 33.3
  17. 17 DeepSeek-V4-Flash max 30.0

Source: Official SuperCLUE-SWE leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 4.8 73.3 high May 2026 Official leaderboard
2 Gemini 3.1 Pro 66.7 high Feb 2026 Official leaderboard
3 Qwen3.7-Max 66.7 Thinking May 2026 Official leaderboard
4 GLM-5.2 63.3 max Jun 2026 Official leaderboard
5 Claude Opus 4.7 60.0 high Apr 2026 Official leaderboard
6 Kimi K2.7 Code 56.7 Jun 2026 Official leaderboard
7 Kimi K2.6 53.3 thinking Apr 2026 Official leaderboard
8 DeepSeek-V4-Pro 53.3 max Apr 2026 Official leaderboard
9 Doubao-Seed-2.0-pro-260215(high) 50.0 high Official leaderboard
10 Gemini 3.5 Flash 50.0 high May 2026 Official leaderboard
11 GPT-5.5 43.3 high Apr 2026 Official leaderboard
12 GLM-5.1 40.0 Apr 2026 Official leaderboard
13 Step 3.7 Flash 40.0 high May 2026 Official leaderboard
14 Grok 4.3 36.7 Apr 2026 Official leaderboard
15 Step 3.5 Flash 33.3 Feb 2026 Official leaderboard
16 MiMo-V2.5-Pro 33.3 Apr 2026 Official leaderboard
17 DeepSeek-V4-Flash 30.0 max Apr 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 4.8 73.3 high May 2026 Official leaderboard
2 Gemini 3.1 Pro 66.7 high Feb 2026 Official leaderboard
3 Qwen3.7-Max 66.7 Thinking May 2026 Official leaderboard
4 GLM-5.2 63.3 max Jun 2026 Official leaderboard
5 Claude Opus 4.7 60.0 high Apr 2026 Official leaderboard
6 Kimi K2.7 Code 56.7 Jun 2026 Official leaderboard
7 Kimi K2.6 53.3 thinking Apr 2026 Official leaderboard
8 DeepSeek-V4-Pro 53.3 max Apr 2026 Official leaderboard
9 Gemini 3.5 Flash 50.0 high May 2026 Official leaderboard
10 GPT-5.5 43.3 high Apr 2026 Official leaderboard
11 GLM-5.1 40.0 Apr 2026 Official leaderboard
12 Step 3.7 Flash 40.0 high May 2026 Official leaderboard
13 Grok 4.3 36.7 Apr 2026 Official leaderboard
14 Step 3.5 Flash 33.3 Feb 2026 Official leaderboard
15 MiMo-V2.5-Pro 33.3 Apr 2026 Official leaderboard
16 DeepSeek-V4-Flash 30.0 max Apr 2026 Official leaderboard

Rankings by part

We read 9 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 完成数, 完成率 and 异常数. Claude Opus 4.8 leads 3 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

完成数

16 models we track have a score here.

  1. 1 Grok 4.3 ↑12 30.0
  2. 2 Gemini 3.1 Pro 29.0
  3. 3 Claude Opus 4.7 ↑2 28.0
  4. 4 Qwen3.7-Max ↓1 28.0
  5. 5 Claude Opus 4.8 ↓4 28.0
  6. 6 Kimi K2.7 Code 28.0
  7. 7 GLM-5.1 ↑4 27.0
  8. 8 GPT-5.5 ↑2 27.0
  9. 9 MiMo-V2.5-Pro ↑6 27.0
  10. 10 DeepSeek-V4-Pro ↓2 27.0

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

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

StepFun Google DeepMind Anthropic
Own leaderboard Not tested since Jun 2026

Source: Official SuperCLUE-SWE leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard
30.0 40.0 50.0 60.0 70.0 80.0 2026 30.0 40.0 50.0 60.0 70.0 80.0 2026

Source: Official SuperCLUE-SWE leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Coding

All 523 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

Data audit

8 of 9 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (17 entries).
  • Pass Models scored 16 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from June 2026, for GLM-5.2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 16 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check