LLM Thematic Generalization Benchmark v2
Models rank eight candidates using three positive examples and three counterexamples. Version 2 filters ambiguous prompts and reports a harder subset of 703 items.
The April 16, 2026 leaderboard reports Claude, GPT, Gemini and other models. Claude Opus 4.6 led the hard subset with an inverse-rank score of 80.6.
- Made by
- Lech Mazur
- Released
- March 2026
- Kind
- Language reasoning
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- A version of another benchmark
- Strongest model tested
- GPT-5.4 #28 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 4.6 leads with 80.6 among models released by April 2026 Claude Opus 4.6 leads with 80.6 among models released by April 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. 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 April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 80.6 Claude Opus 4.6
- 80.0 GPT-5.4
- 79.4
Gemini 3.1 Pro
- 76.3 Claude Sonnet 4.6
- 72.8 Claude Opus 4.7
- 69.8 GLM-5.1
- 69.4 Kimi K2.5
- 65.1
Qwen3.5 397B-A17B
- 65.0
DeepSeek-V3.2
- 63.8 Grok 4.20
- 63.3
Gemini 3.1 Flash-Lite
- 61.7 GPT-5.4 Mini
- 59.5
Qwen 3.6 Plus
- 57.1 ByteDance Seed2.0 Pro
- 53.0
Gemma 4 31B IT
- 51.2
Qwen3.5-122B-A10B
- 45.9 Xiaomi MiMo V2 Pro
- 45.5
Qwen3.5-27B
- 41.7 Baidu Ernie 5.0
- 41.6 Arcee Trinity Large Thinking
- 39.3
MiniMax-M2.7
- 23.0
Mistral Large 3
- 22.0 Grok 4.20 0309
- 20.3
Mistral Medium 3.1
- 1 Claude Opus 4.6 high reasoning 80.6
- 2 GPT-5.4 xhigh reasoning 80.0
- 3
Gemini 3.1 Pro 79.4
- 4 Claude Sonnet 4.6 high reasoning 76.3
- 5 Claude Opus 4.7 high reasoning 72.8
- 6 GLM-5.1 69.8
- 7 Kimi K2.5 thinking 69.4
- 8
Qwen3.5 397B-A17B 65.1
- 9
DeepSeek-V3.2 65.0
- 10 Grok 4.20 reasoning 63.8
- 11
Gemini 3.1 Flash-Lite 63.3
- 12 GPT-5.4 Mini xhigh reasoning 61.7
- 13
Qwen 3.6 Plus 59.5
- 14 ByteDance Seed2.0 Pro 57.1
- 15
Gemma 4 31B IT reasoning 53.0
- 16
Qwen3.5-122B-A10B 51.2
- 17 Xiaomi MiMo V2 Pro 45.9
- 18
Qwen3.5-27B 45.5
- 19 Baidu Ernie 5.0 41.7
- 20 Arcee Trinity Large Thinking 41.6
- 21
MiniMax-M2.7 39.3
- 22
Mistral Large 3 23.0
- 23 Grok 4.20 0309 Non-Reasoning 22.0
- 24
Mistral Medium 3.1 20.3
Source: Official LLM Thematic Generalization Benchmark v2 leaderboard
- 80.6 Claude Opus 4.6
- 80.0 GPT-5.4
- 79.4
Gemini 3.1 Pro
- 76.3 Claude Sonnet 4.6
- 72.8 Claude Opus 4.7
- 69.8 GLM-5.1
- 69.4 Kimi K2.5
- 65.1
Qwen3.5 397B-A17B
- 65.0
DeepSeek-V3.2
- 63.8 Grok 4.20
- 63.3
Gemini 3.1 Flash-Lite
- 61.7 GPT-5.4 Mini
- 59.5
Qwen 3.6 Plus
- 53.0
Gemma 4 31B IT
- 51.2
Qwen3.5-122B-A10B
- 45.5
Qwen3.5-27B
- 39.3
MiniMax-M2.7
- 23.0
Mistral Large 3
- 20.3
Mistral Medium 3.1
- 1 Claude Opus 4.6 high reasoning 80.6
- 2 GPT-5.4 xhigh reasoning 80.0
- 3
Gemini 3.1 Pro 79.4
- 4 Claude Sonnet 4.6 high reasoning 76.3
- 5 Claude Opus 4.7 high reasoning 72.8
- 6 GLM-5.1 69.8
- 7 Kimi K2.5 thinking 69.4
- 8
Qwen3.5 397B-A17B 65.1
- 9
DeepSeek-V3.2 65.0
- 10 Grok 4.20 reasoning 63.8
- 11
Gemini 3.1 Flash-Lite 63.3
- 12 GPT-5.4 Mini xhigh reasoning 61.7
- 13
Qwen 3.6 Plus 59.5
- 14
Gemma 4 31B IT reasoning 53.0
- 15
Qwen3.5-122B-A10B 51.2
- 16
Qwen3.5-27B 45.5
- 17
MiniMax-M2.7 39.3
- 18
Mistral Large 3 23.0
- 19
Mistral Medium 3.1 20.3
Source: Official LLM Thematic Generalization Benchmark v2 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 80.6 | high reasoning | Feb 2026 | Official leaderboard |
| 2 | GPT-5.4 | 80.0 | xhigh reasoning | Mar 2026 | Official leaderboard |
| 3 | | 79.4 | Feb 2026 | Official leaderboard | |
| 4 | Claude Sonnet 4.6 | 76.3 | high reasoning | Feb 2026 | Official leaderboard |
| 5 | Claude Opus 4.7 | 72.8 | high reasoning | Apr 2026 | Official leaderboard |
| 6 | GLM-5.1 | 69.8 | Apr 2026 | Official leaderboard | |
| 7 | Kimi K2.5 | 69.4 | thinking | Jan 2026 | Official leaderboard |
| 8 | | 65.1 | Feb 2026 | Official leaderboard | |
| 9 | | 65.0 | Dec 2025 | Official leaderboard | |
| 10 | Grok 4.20 | 63.8 | reasoning | Feb 2026 | Official leaderboard |
| 11 | | 63.3 | Mar 2026 | Official leaderboard | |
| 12 | GPT-5.4 Mini | 61.7 | xhigh reasoning | Mar 2026 | Official leaderboard |
| 13 | | 59.5 | Mar 2026 | Official leaderboard | |
| 14 | ByteDance Seed2.0 Pro | 57.1 | Official leaderboard | ||
| 15 | | 53.0 | reasoning | Apr 2026 | Official leaderboard |
| 16 | | 51.2 | Feb 2026 | Official leaderboard | |
| 17 | Xiaomi MiMo V2 Pro | 45.9 | Official leaderboard | ||
| 18 | | 45.5 | Feb 2026 | Official leaderboard | |
| 19 | Baidu Ernie 5.0 | 41.7 | Official leaderboard | ||
| 20 | Arcee Trinity Large Thinking | 41.6 | Official leaderboard | ||
| 21 | | 39.3 | Mar 2026 | Official leaderboard | |
| 22 | | 23.0 | Dec 2025 | Official leaderboard | |
| 23 | Grok 4.20 0309 | 22.0 | Non-Reasoning | Official leaderboard | |
| 24 | | 20.3 | Aug 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 80.6 | high reasoning | Feb 2026 | Official leaderboard |
| 2 | GPT-5.4 | 80.0 | xhigh reasoning | Mar 2026 | Official leaderboard |
| 3 | | 79.4 | Feb 2026 | Official leaderboard | |
| 4 | Claude Sonnet 4.6 | 76.3 | high reasoning | Feb 2026 | Official leaderboard |
| 5 | Claude Opus 4.7 | 72.8 | high reasoning | Apr 2026 | Official leaderboard |
| 6 | GLM-5.1 | 69.8 | Apr 2026 | Official leaderboard | |
| 7 | Kimi K2.5 | 69.4 | thinking | Jan 2026 | Official leaderboard |
| 8 | | 65.1 | Feb 2026 | Official leaderboard | |
| 9 | | 65.0 | Dec 2025 | Official leaderboard | |
| 10 | Grok 4.20 | 63.8 | reasoning | Feb 2026 | Official leaderboard |
| 11 | | 63.3 | Mar 2026 | Official leaderboard | |
| 12 | GPT-5.4 Mini | 61.7 | xhigh reasoning | Mar 2026 | Official leaderboard |
| 13 | | 59.5 | Mar 2026 | Official leaderboard | |
| 14 | | 53.0 | reasoning | Apr 2026 | Official leaderboard |
| 15 | | 51.2 | Feb 2026 | Official leaderboard | |
| 16 | | 45.5 | Feb 2026 | Official leaderboard | |
| 17 | | 39.3 | Mar 2026 | Official leaderboard | |
| 18 | | 23.0 | Dec 2025 | Official leaderboard | |
| 19 | | 20.3 | Aug 2025 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official LLM Thematic Generalization Benchmark v2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 4.6 | high reasoning | 80.6 | |||
| GPT-5.4 | xhigh reasoning | 80.0 | |||
| 79.4 | |||||
| GPT-5.4 | high reasoning | 77.4 | |||
| Claude Sonnet 4.6 | high reasoning | 76.3 | |||
| GPT-5.4 | medium reasoning | 75.2 | |||
| Claude Opus 4.7 | high reasoning | 72.8 | |||
| GLM-5.1 | 69.8 | ||||
| Kimi K2.5 | thinking | 69.4 | |||
| Claude Opus 4.6 | no reasoning | 68.8 | |||
| Claude Sonnet 4.6 | no reasoning | 68.5 | |||
| 65.1 | |||||
| 65.0 | |||||
| Grok 4.20 | reasoning | 63.8 | |||
| 63.3 | |||||
| GPT-5.4 Mini | xhigh reasoning | 61.7 | |||
| 59.5 | |||||
| reasoning | 53.0 | ||||
| Claude Opus 4.7 | no reasoning | 52.6 | |||
| 51.2 | |||||
| 45.5 | |||||
| 39.3 | |||||
| GPT-5.4 | no reasoning | 27.1 | |||
| 23.0 | |||||
| 20.3 |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official LLM Thematic Generalization Benchmark v2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 4.6 | high reasoning | 80.6 | |||
| GPT-5.4 | xhigh reasoning | 80.0 | |||
| 79.4 | |||||
| GPT-5.4 | high reasoning | 77.4 | |||
| Claude Sonnet 4.6 | high reasoning | 76.3 | |||
| GPT-5.4 | medium reasoning | 75.2 | |||
| Claude Opus 4.7 | high reasoning | 72.8 | |||
| GLM-5.1 | 69.8 | ||||
| Kimi K2.5 | thinking | 69.4 | |||
| Claude Opus 4.6 | no reasoning | 68.8 | |||
| Claude Sonnet 4.6 | no reasoning | 68.5 | |||
| 65.1 | |||||
| 65.0 | |||||
| Grok 4.20 | reasoning | 63.8 | |||
| 63.3 | |||||
| GPT-5.4 Mini | xhigh reasoning | 61.7 | |||
| 59.5 | |||||
| reasoning | 53.0 | ||||
| Claude Opus 4.7 | no reasoning | 52.6 | |||
| 51.2 | |||||
| 45.5 | |||||
| 39.3 | |||||
| GPT-5.4 | no reasoning | 27.1 | |||
| 23.0 | |||||
| 20.3 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LLM Thematic Generalization Benchmark v2 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official LLM Thematic Generalization Benchmark v2 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
- 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 7 months ago, in April 2026, for Claude Opus 4.7. 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 (24 entries).
- Pass Models scored 19 models we track, plus 5 other entries on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Claude Opus 4.7.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 25 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.