Ideation Arena - Specificity: leaderboard
Metric: Elo (Bradley-Terry over expert pairwise votes). Source: arxiv.org. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 1275.3 |
| 2 | Claude Opus 4.5 | 1240.3 |
| 3 | Claude Sonnet 4.5 | 1214.7 |
| 4 | Kimi K2 (Thinking) | 1118.6 |
| 5 | Mistral Large 3 | 1106.3 |
| 6 | DeepSeek V3.2 | 1071.3 |
| 7 | GLM-4.7 | 1059.9 |
| 8 | O3 | 1059.6 |
| 9 | Gemini 3 Flash (Preview) | 1055.3 |
| 10 | Grok 4 Fast | 1049.8 |
| 11 | Gemini 3 Pro (Preview) | 1031.5 |
| 12 | Grok 4 | 962.8 |
| 13 | Qwen 3 Max | 950.2 |
| 14 | GPT-4o | 836.2 |
Interactive version: theaggregate.ai/benchmark?slug=ideation-arena-specificity · How It Works · Data refreshed daily, snapshot 2026-09-19.