Benchmark Almanac

SuperCLUE-DeepSWE

Not in model cards

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
In and out
Text, Code → Code, Actions
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
10
Entries on its own leaderboard, 2 models we track

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.

  1. 1 GPT-6.1 Sol max / 套餐 / 3小时 84.3
  2. 2 Claude Code + Kimi K3.1 Pro max / 套餐 / 3小时 70.6
  3. 3 Claude Code + DeepSeek V4.1 Flash 1017 max / api / 3小时 64.7
  4. 4 Claude Haiku 5.5 max / api / 3小时 52.9
  5. 5 Claude Code + MiniMax-M3.1-Flash max / 套餐 / 3小时 47.1
  6. 6 Claude Code + Qwen3.8 Max (0902) 套餐 / 3小时 45.1
  7. 7 Claude Code + LongCat-2.5 api / 3小时 45.1
  8. 8 Claude Code + MiMo-V2.6 Pro api / 3小时 43.1
  9. 9 Claude Code + Kimi K3 max / 新套餐 / 3小时 41.2
  10. 10 Claude Code + DeepSeek V4.1 Flash max / api / 3小时 39.2

Source: Official SuperCLUE-DeepSWE leaderboard

Source: Official SuperCLUE-DeepSWE leaderboard

#EntryScoreSettingReleasedRun onSource
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
#ModelScoreSettingReleasedRun onSource
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.

On the benchmark’s own leaderboard
50.0 60.0 70.0 80.0 90.0 50.0 60.0 70.0 80.0 90.0

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

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 (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.

How we check