Benchmark Almanac

GAOKAO-Eval 2024

Qwen2-72B 476.5 leads since June 2024
Not in model cards

Models take Chinese national college entrance examinations. High school teachers grade the open responses.

Released
June 2024
Kind
Exam questions
Level
School
Scored
Graded by people
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-4o May 2024 #162 on the capability index
Last model added
June 2024
Scores refreshed
November 20th, 2026
8
Entries on its own leaderboard, 3 models we track

Qwen2-72B leads with 476.5 among models released by June 2024 Qwen2-72B leads with 476.5 among models released by June 2024

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The authors rank each paper by science total. The headline averages the New Curriculum and National A science totals. 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 June 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 Qwen2-72B 476.5
  2. 2 GPT-4o May 2024 476.3
  3. 3 InternLM2-WQX-20B + InternLM2-WQX-VL-20B 465.3
  4. 4 Qwen2-72B + Qwen-VL-Chat 428.0
  5. 5 GLM-4-9B-Chat + GLM-4V-9B 380.3
  6. 6 Mixtral 8x22B 372.0
  7. 7 Yi-1.5-34B-Chat + Yi-VL-34B 367.8
  8. 8 Qwen2-57B-A14B-Instruct + Qwen-VL-Chat 367.0

Source: Official GAOKAO-Eval 2024 leaderboard

Source: Official GAOKAO-Eval 2024 leaderboard

#EntryScoreSettingDateSource
1 Qwen2-72B 476.5 Jun 2024 Official leaderboard
2 GPT-4o May 2024 476.3 May 2024 Official leaderboard
3 InternLM2-WQX-20B + InternLM2-WQX-VL-20B 465.3 Official leaderboard
4 Qwen2-72B + Qwen-VL-Chat 428.0 Official leaderboard
5 GLM-4-9B-Chat + GLM-4V-9B 380.3 Official leaderboard
6 Mixtral 8x22B 372.0 Apr 2024 Official leaderboard
7 Yi-1.5-34B-Chat + Yi-VL-34B 367.8 Official leaderboard
8 Qwen2-57B-A14B-Instruct + Qwen-VL-Chat 367.0 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen2-72B 476.5 Jun 2024 Official leaderboard
2 GPT-4o May 2024 476.3 May 2024 Official leaderboard
3 Mixtral 8x22B 372.0 Apr 2024 Official leaderboard

Rankings by part

We read 22 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as New Curriculum Chinese, New Curriculum Mathematics and New Curriculum English. Qwen2-72B leads 13 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

New Curriculum Chinese

3 models we track have a score here.

  1. 1 Qwen2-72B 124.0
  2. 2 GPT-4o May 2024 111.5
  3. 3 Mixtral 8x22B 77.5

2 models have held number one on the official leaderboard since its release in June 2024

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

OpenAI Qwen
Own leaderboard Not tested since Jun 2024
Qwen2-72B 476.5

Source: Official GAOKAO-Eval 2024 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
350.0 400.0 450.0 500.0 2024 350.0 400.0 450.0 500.0 2024

Source: Official GAOKAO-Eval 2024 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in June 2024, for Qwen2-72B. Every benchmark

Catalog record 2 pass
  • Pass Task access All 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 (8 entries).
  • Pass Models scored 3 models we track, plus 5 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in June 2024, for Qwen2-72B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4o (#162).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 3 rows for models we track and 5 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