Benchmark Almanac

SuperCLUE-Code3

GPT-4 Turbo (Jan 2024) 68% leads since February 2024
Not in model cards

Models write executable Python functions from Chinese specifications. Unit tests check functionality, and the leaderboard reports results by difficulty.

The comparison includes weighted scores and separate instruction-following results.

Made by
SuperCLUE team
Released
February 2024
Kind
Function-level problems
Level
School
Scored
Checked automatically
Answers
Code
Measures
Capability
Language
Chinese
In and out
Text, Code → Code
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Strongest model tested
GPT-4 Jun 2023 #186 on the capability index
Last model added
January 2024
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 8 models we track

GPT-4 Turbo (Jan 2024) leads with 68% among models released by January 2024 GPT-4 Turbo (Jan 2024) leads with 68% among models released by January 2024

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 January 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-4 Turbo (Jan 2024) 68%
  2. 2 GPT-4 Jun 2023 63.7%
  3. 3 GPT-3.5 Turbo Jan 2024 55.5%
  4. 4 DeepSeek Coder 6.7B 47.8%
  5. 5 Gemini 1.0 Pro 46.5%
  6. 6 XVERSE-13B-2-Chat 30.5%
  7. 7 Qwen-14B 24.7%
  8. 8 Code-Llama-13b-instruct 21.1%
  9. 9 ChatGLM3-6B 15.3%
  10. 10 Baichuan2-13B-Chat 13.9%
  11. 11 Llama2-13b-Chat 6.06%

Source: Official SuperCLUE-Code3 leaderboard

#EntryScoreSettingDateSource
1 GPT-4 Turbo (Jan 2024) 68% Jan 2024 Official leaderboard
2 GPT-4 Jun 2023 63.7% Jun 2023 Official leaderboard
3 GPT-3.5 Turbo Jan 2024 55.5% Jan 2024 Official leaderboard
4 DeepSeek Coder 6.7B 47.8% Nov 2023 Official leaderboard
5 Gemini 1.0 Pro 46.5% Dec 2023 Official leaderboard
6 XVERSE-13B-2-Chat 30.5% Official leaderboard
7 Qwen-14B 24.7% Sep 2023 Official leaderboard
8 Code-Llama-13b-instruct 21.1% Official leaderboard
9 ChatGLM3-6B 15.3% Oct 2023 Official leaderboard
10 Baichuan2-13B-Chat 13.9% Sep 2023 Official leaderboard
11 Llama2-13b-Chat 6.06% Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4 Turbo (Jan 2024) 68% Jan 2024 Official leaderboard
2 GPT-4 Jun 2023 63.7% Jun 2023 Official leaderboard
3 GPT-3.5 Turbo Jan 2024 55.5% Jan 2024 Official leaderboard
4 DeepSeek Coder 6.7B 47.8% Nov 2023 Official leaderboard
5 Gemini 1.0 Pro 46.5% Dec 2023 Official leaderboard
6 Qwen-14B 24.7% Sep 2023 Official leaderboard
7 ChatGLM3-6B 15.3% Oct 2023 Official leaderboard
8 Baichuan2-13B-Chat 13.9% Sep 2023 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: 初级难度, 中级难度 and 高级难度. Each ranks models on one part of the test. GPT-4 Turbo (Jan 2024) leads 2 of them, and GPT-4 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

初级难度

8 models we track have a score here.

  1. 1 GPT-4 Jun 2023 ↑1 90%
  2. 2 GPT-4 Turbo (Jan 2024) ↓1 88.9%
  3. 3 GPT-3.5 Turbo Jan 2024 82.2%
  4. 4 Gemini 1.0 Pro ↑1 68.9%
  5. 5 DeepSeek Coder 6.7B ↓1 67.8%
  6. 6 Qwen-14B 57.8%
  7. 7 Baichuan2-13B-Chat ↑1 43.5%
  8. 8 ChatGLM3-6B ↓1 32.2%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Feb 2024

Source: Official SuperCLUE-Code3 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 Best so far
0% 20% 40% 60% 80% 100% 2023 2024 Near the ceiling (85%) GPT-4 Turbo (Jan 2024) GPT-4 0% 20% 40% 60% 80% 100% 2023 2024 Near the ceiling (85%) GPT-4 Turbo (Jan 2024)

Source: Official SuperCLUE-Code3 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 10 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 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 8 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in January 2024, for GPT-3.5 Turbo.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 (#186).
  • Pass Headroom The best is 68%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 8 rows for models we track and 3 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