Benchmark Almanac

pCLUE

Human 81.2% tops its leaderboard
Not in model cards

Models follow Chinese prompts for classification, inference, generation and reading comprehension. The leaderboard combines exact match and accuracy across tasks.

The pCLUE repository has 509 stars. The team provides a public test set and a submission leaderboard.

Made by
SuperCLUE
Released
October 2022
Kind
Reading in many languages
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
Public, plus a private test set
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
45
Entries on its own leaderboard, 0 models we track

Human tops the leaderboard with 81.2%

Best score per entry from the benchmark's own leaderboard, read on November 21st, 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.

  1. 1 Human 81.2%
  2. 2 nlutest2-large-gen 58.9%
  3. 3 nlutest2-gen 56.9%
  4. 4 pvpvpvpv 56.1%
  5. 5 hemu_pclue_merge 55.2%
  6. 6 p_10_2_12 55%
  7. 7 multi_rm_20_2_12 54.9%
  8. 8 base_test_transformer_3_24_m 54.8%
  9. 9 multi_fv_10_2_12 54.8%
  10. 10 pclue_mengzi_param7-true 54.8%
  11. 11 hemu_pclue_new 54.8%
  12. 12 p_20?_2_12 54.7%
  13. 13 multi_rm_10_2_12 54.7%
  14. 14 pclue_mengzi_param5 54.7%
  15. 15 pclue_mengzi_param6 54.7%
  16. 16 pclue_mengzi_param7 54.7%
  17. 17 single_rm_10_2_12 54.7%
  18. 18 pclue_mengzi_param4 54.6%
  19. 19 imx-4 54.6%
  20. 20 ixm 54.6%
  21. 21 mmodel 54.6%
  22. 22 p_random_10_2_12 54.5%
  23. 23 pclue_mengzi_param3 54.4%
  24. 24 p_10_3_7 54.3%
  25. 25 pclue_mengzi_param2 53.8%
  26. 26 p_random_20_2_12 53.7%
  27. 27 xtestm418_2 53.6%
  28. 28 xtestm418_3 53.6%
  29. 29 hemu_pCLUE 53.5%
  30. 30 mm-1 51.8%
  31. 31 base_test_3_21_m 50.1%
  32. 32 base_test_transformer_1_8 50%
  33. 33 baseline(PromptCLUE) 49.5%
  34. 34 base_test_transformer_3_24 49.2%
  35. 35 nlutest2-large 49.1%
  36. 36 base_test_fix_multi 48.4%
  37. 37 xtestm 48.4%
  38. 38 clueai-v1 48.2%
  39. 39 base_test_no_fix_single 47.4%
  40. 40 nlutest2 46.7%
  41. 41 base_test_no_fix_multi 45.6%
  42. 42 nlutest 41%
  43. 43 base_test_nono_fix_single 39.9%
  44. 44 pCLUE-20221102_TEST2 38.1%
  45. 45 nlutest3 28.9%

Source: Official pCLUE leaderboard

#EntryScoreSettingSubmitted byDateLinkSource
1 Human 81.2% CLUE Oct 2022 github.com Official leaderboard
2 nlutest2-large-gen 58.9% nucky Sep 2023 code.alibaba-inc.com Official leaderboard
3 nlutest2-gen 56.9% nucky Aug 2023 code.alibaba-inc.com Official leaderboard
4 pvpvpvpv 56.1% threecolor Nov 2022 github.com Official leaderboard
5 hemu_pclue_merge 55.2% hemu Feb 2023 github.com Official leaderboard
6 p_10_2_12 55% threecolor Nov 2022 github.com Official leaderboard
7 multi_rm_20_2_12 54.9% threecolor Nov 2022 github.com Official leaderboard
8 base_test_transformer_3_24_m 54.8% threecolor Nov 2022 github.com Official leaderboard
9 multi_fv_10_2_12 54.8% threecolor Nov 2022 github.com Official leaderboard
10 pclue_mengzi_param7-true 54.8% cxy Nov 2022 github.com Official leaderboard
11 hemu_pclue_new 54.8% hemu Feb 2023 github.com Official leaderboard
12 p_20?_2_12 54.7% threecolor Nov 2022 github.com Official leaderboard
13 multi_rm_10_2_12 54.7% threecolor Nov 2022 github.com Official leaderboard
14 pclue_mengzi_param5 54.7% cxy Nov 2022 github.com Official leaderboard
15 pclue_mengzi_param6 54.7% cxy Nov 2022 github.com Official leaderboard
16 pclue_mengzi_param7 54.7% cxy Nov 2022 github.com Official leaderboard
17 single_rm_10_2_12 54.7% threecolor Nov 2022 github.com Official leaderboard
18 pclue_mengzi_param4 54.6% cxy Nov 2022 github.com Official leaderboard
19 imx-4 54.6% imx Apr 2023 github.com Official leaderboard
20 ixm 54.6% ixm Apr 2023 github.com Official leaderboard
21 mmodel 54.6% mzy Apr 2023 github.com Official leaderboard
22 p_random_10_2_12 54.5% threecolor Nov 2022 github.com Official leaderboard
23 pclue_mengzi_param3 54.4% cxy Nov 2022 github.com Official leaderboard
24 p_10_3_7 54.3% threecolor Nov 2022 github.com Official leaderboard
25 pclue_mengzi_param2 53.8% cxy Nov 2022 github.com Official leaderboard
26 p_random_20_2_12 53.7% threecolor Nov 2022 github.com Official leaderboard
27 xtestm418_2 53.6% zyxm Apr 2023 Official leaderboard
28 xtestm418_3 53.6% zyxm Apr 2023 Official leaderboard
29 hemu_pCLUE 53.5% hemu Feb 2023 github.com Official leaderboard
30 mm-1 51.8% ixm Apr 2023 github.com Official leaderboard
31 base_test_3_21_m 50.1% threecolor Nov 2022 github.com Official leaderboard
32 base_test_transformer_1_8 50% threecolor Nov 2022 github.com Official leaderboard
33 baseline(PromptCLUE) 49.5% ClueAI Oct 2022 github.com Official leaderboard
34 base_test_transformer_3_24 49.2% threecolor Nov 2022 github.com Official leaderboard
35 nlutest2-large 49.1% nucky Sep 2023 code.alibaba-inc.com Official leaderboard
36 base_test_fix_multi 48.4% threecolor Nov 2022 github.com Official leaderboard
37 xtestm 48.4% zyxm Apr 2023 Official leaderboard
38 clueai-v1 48.2% ClueAI Oct 2022 github.com Official leaderboard
39 base_test_no_fix_single 47.4% threecolor Nov 2022 github.com Official leaderboard
40 nlutest2 46.7% nucky Aug 2023 code.alibaba-inc.com Official leaderboard
41 base_test_no_fix_multi 45.6% threecolor Nov 2022 github.com Official leaderboard
42 nlutest 41% nucky Mar 2023 code.alibaba-inc.com Official leaderboard
43 base_test_nono_fix_single 39.9% threecolor Nov 2022 github.com Official leaderboard
44 pCLUE-20221102_TEST2 38.1% pCLUE-20221102_TEST2 Nov 2022 Official leaderboard
45 nlutest3 28.9% nucky3 Mar 2023 code.alibaba-inc.com Official 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

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (45 entries).
  • Pass Models scored 45 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on cluebenchmarks.com: 45 entries at the last read, none a model we track.
  • Pass Last read November 21st, 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