Benchmark Almanac

COPAL-ID

GPT-4 (snapshot unspecified) 92.1% tops its leaderboard Llama 2-7B 58.9% leads the models we track
Not in model cards

Models choose a plausible cause or consequence in Indonesian scenarios. The questions require familiarity with local customs and expressions.

Released
November 2023
Kind
Reasoning in many languages
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Indonesian
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Llama 2-7B #238 on the capability index
Last model added
July 2023
Scores refreshed
November 20th, 2026
12
Entries in its paper, 1 model we track

GPT-4 (snapshot unspecified) tops the leaderboard with 92.1% Llama 2-7B leads with 58.9%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is Llama 2-7B, at 58.9%. This view shows only models we track, each at its best.

  1. 1 GPT-4 (snapshot unspecified) 5-shot, Monolingual standard 92.1%
  2. 2 ChatGPT 5-shot, Monolingual standard 76.7%
  3. 3 Sailor-7B 5-shot, best prompt, Cross-lingual standard 73.9%
  4. 4 SeaLLM-7B 5-shot, best prompt, Monolingual standard 73.2%
  5. 5 BLOOMZ-7B 5-shot, best prompt, Monolingual standard 66.9%
  6. 6 XLMR-Large Fine-tuned, Monolingual standard 64.2%
  7. 7 Bactrian-X-7B 5-shot, best prompt, Cross-lingual standard 63.7%
  8. 8 PolyLM-13B 5-shot, best prompt, Cross-lingual standard 63.3%
  9. 9 IndoBERT Fine-tuned, Monolingual standard 61%
  10. 10 Llama 2-7B 5-shot, best prompt, Cross-lingual standard 58.9%
  11. 11 XLMR-Base Fine-tuned, Monolingual colloquial 57.4%
  12. 12 mBERT Fine-tuned, Translate-test 56.5%

Source: The COPAL-ID paper

Source: The COPAL-ID paper

#EntryScoreSettingDateSource
1 GPT-4 (snapshot unspecified) 92.1% 5-shot, Monolingual standard Official leaderboard
2 ChatGPT 76.7% 5-shot, Monolingual standard Official leaderboard
3 Sailor-7B 73.9% 5-shot, best prompt, Cross-lingual standard Official leaderboard
4 SeaLLM-7B 73.2% 5-shot, best prompt, Monolingual standard Official leaderboard
5 BLOOMZ-7B 66.9% 5-shot, best prompt, Monolingual standard Official leaderboard
6 XLMR-Large 64.2% Fine-tuned, Monolingual standard Official leaderboard
7 Bactrian-X-7B 63.7% 5-shot, best prompt, Cross-lingual standard Official leaderboard
8 PolyLM-13B 63.3% 5-shot, best prompt, Cross-lingual standard Official leaderboard
9 IndoBERT 61% Fine-tuned, Monolingual standard Official leaderboard
10 Llama 2-7B 58.9% 5-shot, best prompt, Cross-lingual standard Jul 2023 Official leaderboard
11 XLMR-Base 57.4% Fine-tuned, Monolingual colloquial Official leaderboard
12 mBERT 56.5% Fine-tuned, Translate-test Official leaderboard
#ModelScoreSettingDateSource
1 Llama 2-7B 58.9% 5-shot, best prompt, Cross-lingual standard Jul 2023 Official leaderboard

Number one over time

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

Meta
Benchmark paper Not tested since Nov 2023
Llama 2-7B 58.9%

Source: The COPAL-ID paper

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
In the benchmark’s paper
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Llama 2-7B 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Llama 2-7B

Source: Official COPAL-ID 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in July 2023, for Llama 2-7B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 1 model we track, plus 11 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in July 2023, for Llama 2-7B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Llama 2-7B (#238).
  • Pass Headroom The best is 58.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 4 rows for models we track and 11 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