SuperCLUE-SWE with Claude Code
Models solve Chinese software engineering tasks in the Claude Code harness.
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, Claude Code
- Refresh
- One fixed set
- Run by
- A host
- Based on
- SuperCLUE-SWE
- In views
- Agents
- Strongest model tested
- Kimi K3 #25 on the capability index
- Last model added
- August 2026
- Scores refreshed
- November 20th, 2026
Kimi K3 leads with 75.8 among models released by August 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Kimi K3 max / api 75.8
- 2 GLM-5.2 max / api 64.1
- 3
DeepSeek V4 Flash 0731 max / api 59.0
- 4 Kimi K2.7 Code api 55.4
- 5
Seed2.1 Pro high / api 51.6
- 6 MiMo-V2.5-Pro api 49.5
- 7
Qwen 3.8 Max api 49.5
- 8
Qwen3.7-Max Thinking / api 48.4
- 9
DeepSeek-V4-Pro max / api 47.4
- 10
Tencent Hy3 high / api 47.4
- 11
MiniMax-M3 api 46.3
- 12
LongCat-2.0 api 42.1
Source: Official SuperCLUE-SWE with Claude Code leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Kimi K3 | 75.8 | max / api | Jul 2026 | Official leaderboard |
| 2 | GLM-5.2 | 64.1 | max / api | Jun 2026 | Official leaderboard |
| 3 | | 59.0 | max / api | Jul 2026 | Official leaderboard |
| 4 | Kimi K2.7 Code | 55.4 | api | Jun 2026 | Official leaderboard |
| 5 | | 51.6 | high / api | Jun 2026 | Official leaderboard |
| 6 | MiMo-V2.5-Pro | 49.5 | api | Apr 2026 | Official leaderboard |
| 7 | | 49.5 | api | Aug 2026 | Official leaderboard |
| 8 | | 48.4 | Thinking / api | May 2026 | Official leaderboard |
| 9 | | 47.4 | max / api | Apr 2026 | Official leaderboard |
| 10 | | 47.4 | high / api | Jul 2026 | Official leaderboard |
| 11 | | 46.3 | api | Jun 2026 | Official leaderboard |
| 12 | | 42.1 | api | Jul 2026 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: 平均每题交互轮数, 超时题目数量(在规定时间内未完成题目) and 总题目数量. Each ranks models on one part of the test. MiniMax-M3 leads 1 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
平均每题交互轮数
12 models we track have a score here.
- 1
MiniMax-M3 ↑10 75.2
- 2
LongCat-2.0 ↑10 65.8
- 3
Seed2.1 Pro ↑2 62.5
- 4
DeepSeek-V4-Pro ↑5 59.6
- 5
DeepSeek V4 Flash 0731 ↓2 57.1
- 6 Kimi K2.7 Code ↓2 56.3
- 7 GLM-5.2 ↓5 54.9
- 8
Qwen 3.8 Max ↓1 52.8
- 9 MiMo-V2.5-Pro ↓3 44.1
- 10
Tencent Hy3 44.0
超时题目数量(在规定时间内未完成题目)
12 models we track have a score here.
- 1
Qwen 3.8 Max ↑6 34.0
- 2
LongCat-2.0 ↑10 27.0
- 3
Seed2.1 Pro ↑2 17.0
- 4 MiMo-V2.5-Pro ↑2 11.0
- 5
MiniMax-M3 ↑6 11.0
- 6 GLM-5.2 ↓4 9.00
- 7
Qwen3.7-Max ↑1 8.00
- 8 Kimi K3 ↓7 8.00
- 9
DeepSeek V4 Flash 0731 ↓6 8.00
- 10 Kimi K2.7 Code ↓6 7.00
总题目数量
12 models we track have a score here.
- 1 MiMo-V2.5-Pro ↑5 95.0
- 2
DeepSeek-V4-Pro ↑7 95.0
- 3
Qwen3.7-Max ↑5 95.0
- 4
MiniMax-M3 ↑7 95.0
- 5 Kimi K2.7 Code ↓1 95.0
- 6 GLM-5.2 ↓4 95.0
- 7
Seed2.1 Pro ↓2 95.0
- 8
Tencent Hy3 ↑2 95.0
- 9
LongCat-2.0 ↑3 95.0
- 10 Kimi K3 ↓9 95.0
4 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 with Claude Code 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 with Claude Code 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 (12 entries).
- Pass Models scored 12 models we track.
- Pass Newest score The newest is from August 2026, for Qwen 3.8 Max.
- Note Frontier models None of the top 10 has a score. The strongest tested is Kimi K3 (#25).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 12 rows for models we track 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.