SuperCLUE-SWE
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
- 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
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 73.3 Claude Opus 4.8
- 66.7
Gemini 3.1 Pro
- 66.7
Qwen3.7-Max
- 63.3 GLM-5.2
- 60.0 Claude Opus 4.7
- 56.7 Kimi K2.7 Code
- 53.3 Kimi K2.6
- 53.3
DeepSeek-V4-Pro
- 50.0 Doubao-Seed-2.0-pro-260215(high)
- 50.0
Gemini 3.5 Flash
- 43.3 GPT-5.5
- 40.0 GLM-5.1
- 40.0
Step 3.7 Flash
- 36.7 Grok 4.3
- 33.3
Step 3.5 Flash
- 33.3 MiMo-V2.5-Pro
- 30.0
DeepSeek-V4-Flash
- 1 Claude Opus 4.8 high 73.3
- 2
Gemini 3.1 Pro high 66.7
- 3
Qwen3.7-Max Thinking 66.7
- 4 GLM-5.2 max 63.3
- 5 Claude Opus 4.7 high 60.0
- 6 Kimi K2.7 Code 56.7
- 7 Kimi K2.6 thinking 53.3
- 8
DeepSeek-V4-Pro max 53.3
- 9 Doubao-Seed-2.0-pro-260215(high) high 50.0
- 10
Gemini 3.5 Flash high 50.0
- 11 GPT-5.5 high 43.3
- 12 GLM-5.1 40.0
- 13
Step 3.7 Flash high 40.0
- 14 Grok 4.3 36.7
- 15
Step 3.5 Flash 33.3
- 16 MiMo-V2.5-Pro 33.3
- 17
DeepSeek-V4-Flash max 30.0
Source: Official SuperCLUE-SWE leaderboard
- 1 Claude Opus 4.8 high 73.3
- 2
Gemini 3.1 Pro high 66.7
- 3
Qwen3.7-Max Thinking 66.7
- 4 GLM-5.2 max 63.3
- 5 Claude Opus 4.7 high 60.0
- 6 Kimi K2.7 Code 56.7
- 7 Kimi K2.6 thinking 53.3
- 8
DeepSeek-V4-Pro max 53.3
- 9
Gemini 3.5 Flash high 50.0
- 10 GPT-5.5 high 43.3
- 11 GLM-5.1 40.0
- 12
Step 3.7 Flash high 40.0
- 13 Grok 4.3 36.7
- 14
Step 3.5 Flash 33.3
- 15 MiMo-V2.5-Pro 33.3
- 16
DeepSeek-V4-Flash max 30.0
Source: Official SuperCLUE-SWE leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 73.3 | high | May 2026 | Official leaderboard |
| 2 | | 66.7 | high | Feb 2026 | Official leaderboard |
| 3 | | 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 | | 53.3 | max | Apr 2026 | Official leaderboard |
| 9 | Doubao-Seed-2.0-pro-260215(high) | 50.0 | high | Official leaderboard | |
| 10 | | 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 | | 40.0 | high | May 2026 | Official leaderboard |
| 14 | Grok 4.3 | 36.7 | Apr 2026 | Official leaderboard | |
| 15 | | 33.3 | Feb 2026 | Official leaderboard | |
| 16 | MiMo-V2.5-Pro | 33.3 | Apr 2026 | Official leaderboard | |
| 17 | | 30.0 | max | Apr 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 73.3 | high | May 2026 | Official leaderboard |
| 2 | | 66.7 | high | Feb 2026 | Official leaderboard |
| 3 | | 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 | | 53.3 | max | Apr 2026 | Official leaderboard |
| 9 | | 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 | | 40.0 | high | May 2026 | Official leaderboard |
| 13 | Grok 4.3 | 36.7 | Apr 2026 | Official leaderboard | |
| 14 | | 33.3 | Feb 2026 | Official leaderboard | |
| 15 | MiMo-V2.5-Pro | 33.3 | Apr 2026 | Official leaderboard | |
| 16 | | 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 Grok 4.3 ↑12 30.0
- 2
Gemini 3.1 Pro 29.0
- 3 Claude Opus 4.7 ↑2 28.0
- 4
Qwen3.7-Max ↓1 28.0
- 5 Claude Opus 4.8 ↓4 28.0
- 6 Kimi K2.7 Code 28.0
- 7 GLM-5.1 ↑4 27.0
- 8 GPT-5.5 ↑2 27.0
- 9 MiMo-V2.5-Pro ↑6 27.0
- 10
DeepSeek-V4-Pro ↓2 27.0
完成率
16 models we track have a score here.
- 1 Grok 4.3 ↑12 1.00
- 2
Gemini 3.1 Pro 0.97
- 3 Claude Opus 4.7 ↑2 0.93
- 4
Qwen3.7-Max ↓1 0.93
- 5 Claude Opus 4.8 ↓4 0.93
- 6 Kimi K2.7 Code 0.93
- 7 GLM-5.1 ↑4 0.90
- 8 GPT-5.5 ↑2 0.90
- 9 MiMo-V2.5-Pro ↑6 0.90
- 10
DeepSeek-V4-Pro ↓2 0.90
异常数
16 models we track have a score here.
- 1
Step 3.5 Flash ↑13 5.00
- 2 Kimi K2.6 ↑5 5.00
- 3
DeepSeek-V4-Flash ↑13 4.00
- 4
Gemini 3.5 Flash ↑5 4.00
- 5
Step 3.7 Flash ↑7 4.00
- 6 GLM-5.1 ↑5 3.00
- 7 GPT-5.5 ↑3 3.00
- 8 MiMo-V2.5-Pro ↑7 3.00
- 9
DeepSeek-V4-Pro ↓1 3.00
- 10 GLM-5.2 ↓6 3.00
异常率
16 models we track have a score here.
- 1
Step 3.5 Flash ↑13 0.17
- 2 Kimi K2.6 ↑5 0.17
- 3
DeepSeek-V4-Flash ↑13 0.13
- 4
Gemini 3.5 Flash ↑5 0.13
- 5
Step 3.7 Flash ↑7 0.13
- 6 GLM-5.1 ↑5 0.10
- 7 GPT-5.5 ↑3 0.10
- 8 MiMo-V2.5-Pro ↑7 0.10
- 9
DeepSeek-V4-Pro ↓1 0.10
- 10 GLM-5.2 ↓6 0.10
空补丁数
16 models we track have a score here.
- 1 GLM-5.2 ↑3 1.00
- 2
Step 3.5 Flash ↑12 0.00
- 3
Gemini 3.1 Pro ↓1 0.00
- 4 GLM-5.1 ↑7 0.00
- 5 Claude Opus 4.7 0.00
- 6 Kimi K2.6 ↑1 0.00
- 7 GPT-5.5 ↑3 0.00
- 8 MiMo-V2.5-Pro ↑7 0.00
- 9
DeepSeek-V4-Flash ↑7 0.00
- 10
DeepSeek-V4-Pro ↓2 0.00
空补丁率
16 models we track have a score here.
- 1 GLM-5.2 ↑3 0.03
- 2
Step 3.5 Flash ↑12 0.00
- 3
Gemini 3.1 Pro ↓1 0.00
- 4 GLM-5.1 ↑7 0.00
- 5 Claude Opus 4.7 0.00
- 6 Kimi K2.6 ↑1 0.00
- 7 GPT-5.5 ↑3 0.00
- 8 MiMo-V2.5-Pro ↑7 0.00
- 9
DeepSeek-V4-Flash ↑7 0.00
- 10
DeepSeek-V4-Pro ↓2 0.00
解决数
16 models we track have a score here.
- 1 Claude Opus 4.8 22.0
- 2
Gemini 3.1 Pro 20.0
- 3
Qwen3.7-Max 20.0
- 4 GLM-5.2 19.0
- 5 Claude Opus 4.7 18.0
- 6 Kimi K2.7 Code 17.0
- 7 Kimi K2.6 16.0
- 8
DeepSeek-V4-Pro 16.0
- 9
Gemini 3.5 Flash 15.0
- 10 GPT-5.5 13.0
转化率
16 models we track have a score here.
- 1 Claude Opus 4.8 0.79
- 2 GLM-5.2 ↑2 0.73
- 3
Qwen3.7-Max 0.71
- 4
Gemini 3.1 Pro ↓2 0.69
- 5 Claude Opus 4.7 0.64
- 6 Kimi K2.6 ↑1 0.64
- 7 Kimi K2.7 Code ↓1 0.61
- 8
DeepSeek-V4-Pro 0.59
- 9
Gemini 3.5 Flash 0.58
- 10 GPT-5.5 0.48
解决率
16 models we track have a score here.
- 1 Claude Opus 4.8 0.73
- 2
Gemini 3.1 Pro 0.67
- 3
Qwen3.7-Max 0.67
- 4 GLM-5.2 0.63
- 5 Claude Opus 4.7 0.60
- 6 Kimi K2.7 Code 0.57
- 7 Kimi K2.6 0.53
- 8
DeepSeek-V4-Pro 0.53
- 9
Gemini 3.5 Flash 0.50
- 10 GPT-5.5 0.43
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.
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.
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
- 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.