SuperCLUE-SWE with mini-swe-agent
Models solve Chinese software engineering tasks with the mini-swe-agent 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
- Run by
- A host
- Based on
- SuperCLUE-SWE
- In views
- Agents
- Strongest model tested
-
DeepSeek V4.1 Flash 1017 #23 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
DeepSeek V4.1 Flash 1017 leads with 60.0 DeepSeek V4.1 Flash 1017 leads with 60.0
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.
- 1
DeepSeek V4.1 Flash 1017 max 60.0
- 2 Kimi K3 max 56.0
- 3 GLM-5.3 max 56.0
- 4 NebulaCoder-lite-v9-preview 52.0
- 5
Qwen3.8 Max (0902) xhigh 52.0
- 6 Spark-X2.6(thinking) thinking 48.0
- 7
MiniMax-M3.1-Flash max 48.0
- 8
Tencent Hy4 preview high 44.0
- 9 MiMo-V2.6 Pro thinking 44.0
- 10
LongCat-2.5 thinking 36.0
Source: Official SuperCLUE-SWE with mini-swe-agent leaderboard
- 1
DeepSeek V4.1 Flash 1017 max 60.0
- 2 Kimi K3 max 56.0
- 3 GLM-5.3 max 56.0
- 4
Qwen3.8 Max (0902) xhigh 52.0
- 5
MiniMax-M3.1-Flash max 48.0
- 6
Tencent Hy4 preview high 44.0
- 7 MiMo-V2.6 Pro thinking 44.0
- 8
LongCat-2.5 thinking 36.0
Source: Official SuperCLUE-SWE with mini-swe-agent leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 60.0 | max, mini-swe-agent | Oct 2026 | Official leaderboard |
| 2 | Kimi K3 | 56.0 | max, mini-swe-agent | Jul 2026 | Official leaderboard |
| 3 | GLM-5.3 | 56.0 | max, mini-swe-agent | Aug 2026 | Official leaderboard |
| 4 | NebulaCoder-lite-v9-preview | 52.0 | mini-swe-agent | Official leaderboard | |
| 5 | | 52.0 | xhigh, mini-swe-agent | Sep 2026 | Official leaderboard |
| 6 | Spark-X2.6(thinking) | 48.0 | thinking, mini-swe-agent | Official leaderboard | |
| 7 | | 48.0 | max, mini-swe-agent | Oct 2026 | Official leaderboard |
| 8 | | 44.0 | high, mini-swe-agent | Aug 2026 | Official leaderboard |
| 9 | MiMo-V2.6 Pro | 44.0 | thinking, mini-swe-agent | Sep 2026 | Official leaderboard |
| 10 | | 36.0 | thinking, mini-swe-agent | Nov 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 60.0 | max, mini-swe-agent | Oct 2026 | Official leaderboard |
| 2 | Kimi K3 | 56.0 | max, mini-swe-agent | Jul 2026 | Official leaderboard |
| 3 | GLM-5.3 | 56.0 | max, mini-swe-agent | Aug 2026 | Official leaderboard |
| 4 | | 52.0 | xhigh, mini-swe-agent | Sep 2026 | Official leaderboard |
| 5 | | 48.0 | max, mini-swe-agent | Oct 2026 | Official leaderboard |
| 6 | | 44.0 | high, mini-swe-agent | Aug 2026 | Official leaderboard |
| 7 | MiMo-V2.6 Pro | 44.0 | thinking, mini-swe-agent | Sep 2026 | Official leaderboard |
| 8 | | 36.0 | thinking, mini-swe-agent | Nov 2026 | Official leaderboard |
2 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 mini-swe-agent 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 mini-swe-agent 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 (10 entries).
- Pass Models scored 8 models we track, plus 2 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for LongCat-2.5.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek V4.1 Flash 1017 (#23).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 8 rows for models we track and 2 other entries 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.