Benchmark Almanac

SuperCLUE-Project

o3-mini 82.1 leads since January 2025
Not in model cards

Models generate code for complete software projects.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Building whole projects
Level
Expert
Scored
Checked automatically
Answers
Code
Measures
Capability
Language
Chinese
In and out
Text → Code
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Strongest model tested
o4-mini #95 on the capability index
Last model added
April 2025
Scores refreshed
November 20th, 2026
23
Entries on its own leaderboard, 16 models we track

o3-mini leads with 82.1 among models released by April 2025 o3-mini leads with 82.1 among models released by April 2025

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 April 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 o3-mini API 82.1
  2. 2 Gemini 2.5 Pro Mar 2025, API 81.8
  3. 3 Claude 3.7 Sonnet POE 81.6
  4. 4 o4-mini API 81.3
  5. 5 GPT-4.1 API 81.2
  6. 6 DeepSeek-V3 Mar 2025, API 79.4
  7. 7 DeepSeek-R1 API 78.6
  8. 8 Gemini 2.0 Pro API 78.4
  9. 9 Qwen3-235B-A22B API 78.0
  10. 10 Claude 3.5 Sonnet API 77.9
  11. 11 Hunyuan-T1 API 77.9
  12. 12 Qwen3-32B API 77.4
  13. 13 QwQ-32B API 76.5
  14. 14 GPT-4o-latest-128k API 75.5
  15. 15 Qwen-Max-20250125 API 75.2
  16. 16 Qwen3-30B-A3B API 74.9
  17. 17 K1.5 长思考 官网 74.5
  18. 18 Llama 4 Maverick API 73.8
  19. 19 Step R-mini 官网 73.6
  20. 20 Doubao-1.5-pro-256k API 73.4
  21. 21 GLM-Zero-preview API 71.2
  22. 22 Llama 4 Scout API 67.5
  23. 23 Spark4.0-ultra API 66.5

Source: Official SuperCLUE-Project leaderboard

#EntryScoreSettingReleasedRun onSource
1 o3-mini 82.1 API Jan 2025 Feb 2025 Official leaderboard
2 Gemini 2.5 Pro Mar 2025 81.8 API Mar 2025 Mar 2025 Official leaderboard
3 Claude 3.7 Sonnet 81.6 POE Feb 2025 Feb 2025 Official leaderboard
4 o4-mini 81.3 API Apr 2025 Apr 2025 Official leaderboard
5 GPT-4.1 81.2 API Apr 2025 Apr 2025 Official leaderboard
6 DeepSeek-V3 Mar 2025 79.4 API Mar 2025 Mar 2025 Official leaderboard
7 DeepSeek-R1 78.6 API Jan 2025 Feb 2025 Official leaderboard
8 Gemini 2.0 Pro 78.4 API Feb 2025 Feb 2025 Official leaderboard
9 Qwen3-235B-A22B 78.0 API Apr 2025 Apr 2025 Official leaderboard
10 Claude 3.5 Sonnet 77.9 API Jun 2024 Feb 2025 Official leaderboard
11 Hunyuan-T1 77.9 API Mar 2025 Apr 2025 Official leaderboard
12 Qwen3-32B 77.4 API Apr 2025 Apr 2025 Official leaderboard
13 QwQ-32B 76.5 API Mar 2025 Mar 2025 Official leaderboard
14 GPT-4o-latest-128k 75.5 API Feb 2025 Official leaderboard
15 Qwen-Max-20250125 75.2 API Feb 2025 Official leaderboard
16 Qwen3-30B-A3B 74.9 API Apr 2025 Apr 2025 Official leaderboard
17 K1.5 长思考 74.5 官网 Feb 2025 Official leaderboard
18 Llama 4 Maverick 73.8 API Apr 2025 Apr 2025 Official leaderboard
19 Step R-mini 73.6 官网 Feb 2025 Official leaderboard
20 Doubao-1.5-pro-256k 73.4 API Feb 2025 Official leaderboard
21 GLM-Zero-preview 71.2 API Feb 2025 Official leaderboard
22 Llama 4 Scout 67.5 API Apr 2025 Apr 2025 Official leaderboard
23 Spark4.0-ultra 66.5 API Feb 2025 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 o3-mini 82.1 API Jan 2025 Feb 2025 Official leaderboard
2 Gemini 2.5 Pro Mar 2025 81.8 API Mar 2025 Mar 2025 Official leaderboard
3 Claude 3.7 Sonnet 81.6 POE Feb 2025 Feb 2025 Official leaderboard
4 o4-mini 81.3 API Apr 2025 Apr 2025 Official leaderboard
5 GPT-4.1 81.2 API Apr 2025 Apr 2025 Official leaderboard
6 DeepSeek-V3 Mar 2025 79.4 API Mar 2025 Mar 2025 Official leaderboard
7 DeepSeek-R1 78.6 API Jan 2025 Feb 2025 Official leaderboard
8 Gemini 2.0 Pro 78.4 API Feb 2025 Feb 2025 Official leaderboard
9 Qwen3-235B-A22B 78.0 API Apr 2025 Apr 2025 Official leaderboard
10 Claude 3.5 Sonnet 77.9 API Jun 2024 Feb 2025 Official leaderboard
11 Hunyuan-T1 77.9 API Mar 2025 Apr 2025 Official leaderboard
12 Qwen3-32B 77.4 API Apr 2025 Apr 2025 Official leaderboard
13 QwQ-32B 76.5 API Mar 2025 Mar 2025 Official leaderboard
14 Qwen3-30B-A3B 74.9 API Apr 2025 Apr 2025 Official leaderboard
15 Llama 4 Maverick 73.8 API Apr 2025 Apr 2025 Official leaderboard
16 Llama 4 Scout 67.5 API Apr 2025 Apr 2025 Official leaderboard

Rankings by part

We read 8 parts from the benchmark’s own leaderboard in 5 groups: 游戏开发, 快捷工具, 网络应用, 管理系统 and 多媒体编辑. Each ranks models on one part of the test. Gemini 2.5 Pro leads 2 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

功能完整性

16 models we track have a score here.

  1. 1 o4-mini ↑3 84.8
  2. 2 GPT-4.1 ↑3 84.7
  3. 3 Gemini 2.5 Pro Mar 2025 ↓1 84.4
  4. 4 o3-mini ↓3 84.3
  5. 5 Claude 3.7 Sonnet ↓2 82.5
  6. 6 DeepSeek-R1 ↑1 81.7
  7. 7 Qwen3-235B-A22B ↑2 81.4
  8. 8 DeepSeek-V3 Mar 2025 ↓2 81.4
  9. 9 Gemini 2.0 Pro ↓1 80.7
  10. 10 Hunyuan-T1 ↑1 80.1

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.

Anthropic DeepSeek OpenAI
Own leaderboard Not tested since Apr 2025
o3-mini 82.1

Source: Official SuperCLUE-Project leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
65.0 70.0 75.0 80.0 85.0 2024 2025 65.0 70.0 75.0 80.0 85.0 2024 2025

Source: Official SuperCLUE-Project 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

7 of 9 checks pass, 2 warnings. 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 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (23 entries).
  • Pass Models scored 16 models we track, plus 7 other entries on its leaderboard.
  • Warning Newest score The newest came 19 months ago, in April 2025, for Qwen3-235B-A22B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o4-mini (#95).
  • 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 7 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.

How we check