SuperCLUE-DeepSWE
Agents complete extended 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-6.1 Sol #6 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
GPT-6.1 Sol leads with 84.3 GPT-6.1 Sol leads with 84.3
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as Claude Code + Kimi K3.1 Pro, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
- 84.3 GPT-6.1 Sol
- 70.6 Claude Code + Kimi K3.1 Pro
- 64.7 Claude Code + DeepSeek V4.1 Flash 1017
- 52.9 Claude Haiku 5.5
- 47.1 Claude Code + MiniMax-M3.1-Flash
- 45.1 Claude Code + Qwen3.8 Max (0902)
- 45.1 Claude Code + LongCat-2.5
- 43.1 Claude Code + MiMo-V2.6 Pro
- 41.2 Claude Code + Kimi K3
- 39.2 Claude Code + DeepSeek V4.1 Flash
- 1 GPT-6.1 Sol max / 套餐 / 3小时 84.3
- 2 Claude Code + Kimi K3.1 Pro max / 套餐 / 3小时 70.6
- 3 Claude Code + DeepSeek V4.1 Flash 1017 max / api / 3小时 64.7
- 4 Claude Haiku 5.5 max / api / 3小时 52.9
- 5 Claude Code + MiniMax-M3.1-Flash max / 套餐 / 3小时 47.1
- 6 Claude Code + Qwen3.8 Max (0902) 套餐 / 3小时 45.1
- 7 Claude Code + LongCat-2.5 api / 3小时 45.1
- 8 Claude Code + MiMo-V2.6 Pro api / 3小时 43.1
- 9 Claude Code + Kimi K3 max / 新套餐 / 3小时 41.2
- 10 Claude Code + DeepSeek V4.1 Flash max / api / 3小时 39.2
Source: Official SuperCLUE-DeepSWE leaderboard
- 1 GPT-6.1 Sol max / 套餐 / 3小时 84.3
- 2 Claude Haiku 5.5 max / api / 3小时 52.9
Source: Official SuperCLUE-DeepSWE leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | 84.3 | max / 套餐 / 3小时, Codex | Sep 2026 | Oct 2026 | Official leaderboard |
| 2 | Claude Code + Kimi K3.1 Pro | 70.6 | max / 套餐 / 3小时 | Oct 2026 | Oct 2026 | Official leaderboard |
| 3 | Claude Code + DeepSeek V4.1 Flash 1017 | 64.7 | max / api / 3小时 | Oct 2026 | Oct 2026 | Official leaderboard |
| 4 | Claude Haiku 5.5 | 52.9 | max / api / 3小时, Claude Code | Oct 2026 | Oct 2026 | Official leaderboard |
| 5 | Claude Code + MiniMax-M3.1-Flash | 47.1 | max / 套餐 / 3小时 | Oct 2026 | Official leaderboard | |
| 6 | Claude Code + Qwen3.8 Max (0902) | 45.1 | 套餐 / 3小时 | Sep 2026 | Oct 2026 | Official leaderboard |
| 7 | Claude Code + LongCat-2.5 | 45.1 | api / 3小时 | Nov 2026 | Official leaderboard | |
| 8 | Claude Code + MiMo-V2.6 Pro | 43.1 | api / 3小时 | Sep 2026 | Oct 2026 | Official leaderboard |
| 9 | Claude Code + Kimi K3 | 41.2 | max / 新套餐 / 3小时 | Jul 2026 | Oct 2026 | Official leaderboard |
| 10 | Claude Code + DeepSeek V4.1 Flash | 39.2 | max / api / 3小时 | Sep 2026 | Oct 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | 84.3 | max / 套餐 / 3小时, Codex | Sep 2026 | Oct 2026 | Official leaderboard |
| 2 | Claude Haiku 5.5 | 52.9 | max / api / 3小时, Claude Code | Oct 2026 | Oct 2026 | Official 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-DeepSWE 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 2 models we track, plus 8 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
- Note Frontier models Only 1 of the top 10 has a score. The strongest tested is GPT-6.1 Sol (#6).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 10 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.