LLM Divergent Thinking Creativity Benchmark
Models generate sets of words that differ in meaning.
The author publishes the model comparison in the repository.
- Made by
- Lech Mazur
- Kind
- Creative writing
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- o1-mini #142 on the capability index
- Last model added
- March 2025
- Scores refreshed
- November 20th, 2026
o1-preview leads with 4.79 among models released by March 2025 o1-preview leads with 4.79 among models released by March 2025
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. 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 March 2025, 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
- 4.79 o1-preview
- 4.65
Gemini 2.0 Flash
- 4.47 Claude 3 Opus
- 4.45 Grok-2
- 4.44
Llama 3.3 70B
- 4.41 Claude 3.5 Sonnet
- 4.41
Gemini 2.0 Flash Thinking
- 4.37
Gemma 2 27B
- 4.20 o1-mini
- 4.16 Claude 3.5 Haiku
- 4.14
Mistral Large 2
- 4.12 GPT-4o mini
- 4.09
Gemini 1.5 Flash
- 4.07 Gemini 1.5 Pro (Sept)
- 3.98 Claude 3 Haiku
- 3.89
Qwen2.5-72B
- 3.83
Llama 3.1-405B
- 3.76
DeepSeek-V2.5
- 3.73 GPT-4o
- 1 o1-preview 4.79
- 2
Gemini 2.0 Flash Feb 2025 4.65
- 3 Claude 3 Opus 4.47
- 4 Grok-2 Dec 2024 4.45
- 5
Llama 3.3 70B 4.44
- 6 Claude 3.5 Sonnet 4.41
- 7
Gemini 2.0 Flash Thinking Jan 2025 4.41
- 8
Gemma 2 27B 4.37
- 9 o1-mini 4.20
- 10 Claude 3.5 Haiku 4.16
- 11
Mistral Large 2 Nov 2024 4.14
- 12 GPT-4o mini 4.12
- 13
Gemini 1.5 Flash Sep 2024 4.09
- 14 Gemini 1.5 Pro (Sept) 4.07
- 15 Claude 3 Haiku 3.98
- 16
Qwen2.5-72B 3.89
- 17
Llama 3.1-405B 3.83
- 18
DeepSeek-V2.5 Sep 2024 3.76
- 19 GPT-4o Mar 2025 3.73
Source: Official LLM Divergent Thinking Creativity Benchmark leaderboard
- 4.79 o1-preview
- 4.65
Gemini 2.0 Flash
- 4.47 Claude 3 Opus
- 4.45 Grok-2
- 4.44
Llama 3.3 70B
- 4.41 Claude 3.5 Sonnet
- 4.41
Gemini 2.0 Flash Thinking
- 4.37
Gemma 2 27B
- 4.20 o1-mini
- 4.16 Claude 3.5 Haiku
- 4.14
Mistral Large 2
- 4.12 GPT-4o mini
- 4.09
Gemini 1.5 Flash
- 3.98 Claude 3 Haiku
- 3.89
Qwen2.5-72B
- 3.83
Llama 3.1-405B
- 3.76
DeepSeek-V2.5
- 3.73 GPT-4o
- 1 o1-preview 4.79
- 2
Gemini 2.0 Flash Feb 2025 4.65
- 3 Claude 3 Opus 4.47
- 4 Grok-2 Dec 2024 4.45
- 5
Llama 3.3 70B 4.44
- 6 Claude 3.5 Sonnet 4.41
- 7
Gemini 2.0 Flash Thinking Jan 2025 4.41
- 8
Gemma 2 27B 4.37
- 9 o1-mini 4.20
- 10 Claude 3.5 Haiku 4.16
- 11
Mistral Large 2 Nov 2024 4.14
- 12 GPT-4o mini 4.12
- 13
Gemini 1.5 Flash Sep 2024 4.09
- 14 Claude 3 Haiku 3.98
- 15
Qwen2.5-72B 3.89
- 16
Llama 3.1-405B 3.83
- 17
DeepSeek-V2.5 Sep 2024 3.76
- 18 GPT-4o Mar 2025 3.73
Source: Official LLM Divergent Thinking Creativity Benchmark leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-preview | 4.79 | Sep 2024 | Official leaderboard | |
| 2 | | 4.65 | Feb 2025 | Official leaderboard | |
| 3 | Claude 3 Opus | 4.47 | Feb 2024 | Official leaderboard | |
| 4 | Grok-2 Dec 2024 | 4.45 | Dec 2024 | Official leaderboard | |
| 5 | | 4.44 | Dec 2024 | Official leaderboard | |
| 6 | Claude 3.5 Sonnet | 4.41 | Jun 2024 | Official leaderboard | |
| 7 | | 4.41 | Jan 2025 | Official leaderboard | |
| 8 | | 4.37 | Jun 2024 | Official leaderboard | |
| 9 | o1-mini | 4.20 | Sep 2024 | Official leaderboard | |
| 10 | Claude 3.5 Haiku | 4.16 | Oct 2024 | Official leaderboard | |
| 11 | | 4.14 | Nov 2024 | Official leaderboard | |
| 12 | GPT-4o mini | 4.12 | Jul 2024 | Official leaderboard | |
| 13 | | 4.09 | Aug 2024 | Official leaderboard | |
| 14 | Gemini 1.5 Pro (Sept) | 4.07 | Official leaderboard | ||
| 15 | Claude 3 Haiku | 3.98 | Mar 2024 | Official leaderboard | |
| 16 | | 3.89 | Sep 2024 | Official leaderboard | |
| 17 | | 3.83 | Jul 2024 | Official leaderboard | |
| 18 | | 3.76 | Sep 2024 | Official leaderboard | |
| 19 | GPT-4o Mar 2025 | 3.73 | Mar 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-preview | 4.79 | Sep 2024 | Official leaderboard | |
| 2 | | 4.65 | Feb 2025 | Official leaderboard | |
| 3 | Claude 3 Opus | 4.47 | Feb 2024 | Official leaderboard | |
| 4 | Grok-2 Dec 2024 | 4.45 | Dec 2024 | Official leaderboard | |
| 5 | | 4.44 | Dec 2024 | Official leaderboard | |
| 6 | Claude 3.5 Sonnet | 4.41 | Jun 2024 | Official leaderboard | |
| 7 | | 4.41 | Jan 2025 | Official leaderboard | |
| 8 | | 4.37 | Jun 2024 | Official leaderboard | |
| 9 | o1-mini | 4.20 | Sep 2024 | Official leaderboard | |
| 10 | Claude 3.5 Haiku | 4.16 | Oct 2024 | Official leaderboard | |
| 11 | | 4.14 | Nov 2024 | Official leaderboard | |
| 12 | GPT-4o mini | 4.12 | Jul 2024 | Official leaderboard | |
| 13 | | 4.09 | Aug 2024 | Official leaderboard | |
| 14 | Claude 3 Haiku | 3.98 | Mar 2024 | Official leaderboard | |
| 15 | | 3.89 | Sep 2024 | Official leaderboard | |
| 16 | | 3.83 | Jul 2024 | Official leaderboard | |
| 17 | | 3.76 | Sep 2024 | Official leaderboard | |
| 18 | GPT-4o Mar 2025 | 3.73 | Mar 2025 | Official leaderboard |
2 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LLM Divergent Thinking Creativity Benchmark 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 Divergent Thinking Creativity Benchmark 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 Writing and taste
- Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
- WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
- Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing.
MiniMax-Text-01 81.3%
- DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate.
DeepSeek-V4-Pro 62.6%
- Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
- Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right.
Muse Spark 0.21
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 20 months ago, in March 2025, for GPT-4o. 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 (19 entries).
- Pass Models scored 18 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 20 months ago, in March 2025, for GPT-4o.
- Note Frontier models None of the top 10 has a score. The strongest tested is o1-mini (#142).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 18 rows for models we track and 1 other entry 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.