Benchmark Almanac

TMMLU+ 1.1

Claude Opus 5 96.2% leads since September 2026
Not in model cards
Version 1.1

Models answer traditional Chinese subject questions from a revised exam set. The revision corrects 197 answers and removes 539 questions from the original release.

The authors recomputed results on the 22,203 remaining questions.

Made by
iKala
Released
September 2026
Kind
Knowledge in many languages
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Run by
Anyone
Based on
TMMLU+
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
21
Models scored on its own leaderboard

Claude Opus 5 leads with 96.2% among models released by August 2026

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 August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Opus 5 96.2%
  2. 2 Gemini 3.7 Flash reasoning 90.5%
  3. 3 GPT-5.6 Sol 88.4%
  4. 4 Claude Fable 5 87.1%
  5. 5 DeepSeek V4 Pro 0813 86.4%
  6. 6 Claude Sonnet 5 84.7%
  7. 7 Gemini 3.1 Pro reasoning 84.3%
  8. 8 DeepSeek-V4-Flash 83.5%
  9. 9 Tencent Hy3 83.3%
  10. 10 GPT-5.6 Terra 82.4%
  11. 11 Kimi K3 81%
  12. 12 Qwen3.7-Max 80.6%
  13. 13 Qwen 3.8 27B 80%
  14. 14 GPT-5.6 Luna 79.6%
  15. 15 GLM-5.2 78.6%
  16. 16 MiMo-V2.5 78.1%
  17. 17 Grok 4.3 76.4%
  18. 18 MiniMax-M3 76.4%
  19. 19 Claude Haiku 4.5 71.7%
  20. 20 Gemma 4 31B IT 69.8%
  21. 21 Nemotron 3 Ultra 67.5%

Source: Official TMMLU+ 1.1 leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5 96.2% Jul 2026 Official leaderboard
2 Gemini 3.7 Flash 90.5% reasoning Aug 2026 Official leaderboard
3 GPT-5.6 Sol 88.4% Jul 2026 Official leaderboard
4 Claude Fable 5 87.1% Jun 2026 Official leaderboard
5 DeepSeek V4 Pro 0813 86.4% Aug 2026 Official leaderboard
6 Claude Sonnet 5 84.7% Jun 2026 Official leaderboard
7 Gemini 3.1 Pro 84.3% reasoning Feb 2026 Official leaderboard
8 DeepSeek-V4-Flash 83.5% Apr 2026 Official leaderboard
9 Tencent Hy3 83.3% Jul 2026 Official leaderboard
10 GPT-5.6 Terra 82.4% Jul 2026 Official leaderboard
11 Kimi K3 81% Jul 2026 Official leaderboard
12 Qwen3.7-Max 80.6% May 2026 Official leaderboard
13 Qwen 3.8 27B 80% Aug 2026 Official leaderboard
14 GPT-5.6 Luna 79.6% Jul 2026 Official leaderboard
15 GLM-5.2 78.6% Jun 2026 Official leaderboard
16 MiMo-V2.5 78.1% Apr 2026 Official leaderboard
17 Grok 4.3 76.4% Apr 2026 Official leaderboard
18 MiniMax-M3 76.4% Jun 2026 Official leaderboard
19 Claude Haiku 4.5 71.7% Oct 2025 Official leaderboard
20 Gemma 4 31B IT 69.8% Apr 2026 Official leaderboard
21 Nemotron 3 Ultra 67.5% Jun 2026 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as STEM, Social Science and Humanities. Claude Opus 5 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

STEM

21 models we track have a score here.

  1. 1 Claude Opus 5 98.7%
  2. 2 Gemini 3.7 Flash 93.4%
  3. 3 GPT-5.6 Sol 93.3%
  4. 4 Qwen 3.8 27B ↑9 93.1%
  5. 5 DeepSeek V4 Pro 0813 92.9%
  6. 6 Claude Fable 5 ↓2 90.6%
  7. 7 GPT-5.6 Terra ↑3 90.2%
  8. 8 Tencent Hy3 ↑1 89.8%
  9. 9 DeepSeek-V4-Flash ↓1 89.4%
  10. 10 Claude Sonnet 5 ↓4 89.2%

Number one over time

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

Anthropic
Own leaderboard Passed 85% in Sep 2026, by Claude Opus 5

Source: Official TMMLU+ 1.1 leaderboard

Claude Fable 5 on the official leaderboard passed 85% in June 2026

Models released before it came out already scored that high. 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% 2026 Near the ceiling (85%) Claude Opus 5 GPT-5.6 Sol Gemini 3.1 Pro Claude Haiku 4.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5 GPT-5.6 Sol

Source: Official TMMLU+ 1.1 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.

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

OpenAI Anthropic
TMMLU+ 1.1 Passed 85% in Sep 2026, by Claude Opus 5
TMMLU+ Passed 85% in Aug 2025, by GPT-5
GPT-5 88.6%
TMMLU+ 1.1 Passed 85% in Sep 2026, by Claude Opus 5

Source: Official leaderboards

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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (21 entries).
  • Pass Models scored 21 models we track.
  • Pass Newest score The newest is from August 2026, for Qwen 3.8 27B.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5 (#11).
  • Note Headroom Saturated. The best is 96.2%, past 85% since June 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 21 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