CreativityPrism benchmark scores 17 frontier and open LLMs across 8 creative tasks
DanielKhashabi · x · 2026-11-12
Researchers released CreativityPrism, a new benchmark for systematically evaluating LLM creativity.
- Covers 3 domains and 8 tasks: divergent thinking (AUT, DAT, TTCT), creative writing (short story, TTCW, Creativity Index), and logical reasoning (NeoCoder, Creative Math)
- Every output is scored along quality, novelty, and diversity — including fluency, originality (thought/form/content), n-gram diversity, and Convergence@k metrics
- 17 frontier and open models have been evaluated so far
More from Research
- DeepMind Podcast: AlphaGenome 2 Helps Scientists Screen Millions of DNA Changes for Rare Disease Causes — GoogleDeepMind · 2026-11-12
- Test-time self-distillation decoding beats beam search by 8.2 pts on MATH500 without training — hbouammar · 2026-11-12
- Anthropic's 'Worse Together': single coordinator agent beats per-user agent teams in all 4 tests — ombre-ai · 2026-11-12
- 1,440 Synthetic Control Specs Show Huge Leeway in California $20 Minimum Wage Studies — RexDouglass · 2026-11-12
- ICLR abstract word-frequency shift: 'novel' and 'comprehensive' plummet as LLM fingerprints fade — y_m_asano · 2026-11-12
- Evolving Infra: agent-adaptive LLM serving cuts latency up to 4.1x vs NVIDIA Dynamo — mit-han-lab · 2026-11-12