Benchmark Almanac

CLEVA

GPT-4 Jun 2023 0.96 leads since August 2023
Not in model cards

Models complete Chinese language tasks including text classification, instruction following, and classical Chinese comprehension. The evaluation samples questions for each round.

Made by
Yanyang Li and colleagues
Released
August 2023
Kind
Knowledge in many languages
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Refresh
Live
Run by
A host
In views
Kept fresh
Strongest model tested
GPT-4 Jun 2023 #186 on the capability index
Last model added
June 2023
Scores refreshed
November 20th, 2026
4
Models scored on its own leaderboard

GPT-4 leads with 0.96 among models released by June 2023

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in June 2023, 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 Jun 2023 0.96
  2. 2 GPT-3.5 Turbo Jun 2023 0.60
  3. 3 LLaMA-65B 0.36
  4. 4 Vicuna-13B-v1.3 0.09

Source: Official CLEVA leaderboard

#ModelScoreSettingDateSource
1 GPT-4 Jun 2023 0.96 Jun 2023 Official leaderboard
2 GPT-3.5 Turbo Jun 2023 0.60 Jun 2023 Official leaderboard
3 LLaMA-65B 0.36 Feb 2023 Official leaderboard
4 Vicuna-13B-v1.3 0.09 Jun 2023 Official leaderboard

Rankings by part

We read 15 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Classical Chinese understanding - EM, Commonsense reasoning - EM and Coreference resolution - EM. GPT-4 leads 13 of them, and GPT-3.5 Turbo leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

Classical Chinese understanding - EM

4 models we track have a score here.

  1. 1 GPT-4 Jun 2023 0.78
  2. 2 LLaMA-65B ↑1 0.68
  3. 3 Vicuna-13B-v1.3 ↑1 0.67
  4. 4 GPT-3.5 Turbo Jun 2023 ↓2 0.51

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 Aug 2023
GPT-4 0.96

Source: Official CLEVA 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
0.00 0.20 0.40 0.60 0.80 1.00 2023 0.00 0.20 0.40 0.60 0.80 1.00 2023

Source: Official CLEVA 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 Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in June 2023, for Vicuna-13B-v1.3. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (4 entries).
  • Note Models scored Only 4 models we track.
  • Warning Newest score The newest came 3 years ago, in June 2023, for Vicuna-13B-v1.3.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 (#186).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on crfm.stanford.edu: 4 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