AgentIdeaBench - Static - Specificity: leaderboard
Specificity dimension of AgentIdeaBench's Static track, where the model is handed the references for a subfield (arXiv 2609.07611v1). Mean LLM-critic score on a 1-10 scale, dropping the highest of three critics and averaging over ideas and subfields, from the static_dims field of reports/leaderboard_full.json; higher is better.
Metric: Specificity Critic Score (1-10). Source: moyunxiang.com. Saturation forecast: Around July 2027. 63 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 7.45 | #22 |
| 2 | GPT-5.6 Terra | 7.31 | #40 |
| 3 | Claude Opus 5 | 7.26 | #16 |
| 4 | GPT-5.6 Luna | 7.19 | #79 |
| 5 | GPT-5 | 7.12 | #105 |
| 6 | GPT-5.5 | 7.04 | #33 |
| 7 | GPT-5.4 | 6.57 | #83 |
| 8 | GPT-5.2 | 6.55 | #115 |
| 9 | Claude Sonnet 5 | 6.25 | #65 |
| 10 | GPT-5.4 Mini | 6.18 | #228 |
| 11 | GPT-5 Mini | 6.15 | #193 |
| 12 | Claude Opus 4.7 | 6.12 | #51 |
| 13 | Claude Opus 4.6 | 6.05 | #67 |
| 14 | O3 | 6 | #132 |
| 15 | Gemini 3.5 Flash | 5.99 | #66 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=agentideabench-static-specificity · How It Works · Data refreshed daily, snapshot 2026-11-05.