AgentIdeaBench - Static - Feasibility: leaderboard
Feasibility 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: Feasibility Critic Score (1-10). Source: moyunxiang.com. Saturation forecast: Not forecast. 63 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Terra | 6.53 | #40 |
| 2 | GPT-5.6 Luna | 6.48 | #79 |
| 3 | GPT-5.6 Sol | 6.31 | #22 |
| 4 | GPT-5 | 6.08 | #105 |
| 5 | Claude Opus 5 | 5.95 | #16 |
| 6 | GPT-5.5 | 5.93 | #33 |
| 7 | Claude Sonnet 5 | 5.78 | #65 |
| 8 | GPT-4o | 5.77 | #357 |
| 9 | Claude Opus 4.6 | 5.75 | #67 |
| 10 | GPT-5.4 | 5.68 | #83 |
| 11 | GPT-5.2 | 5.68 | #115 |
| 12 | GPT-5 Nano | 5.62 | #439 |
| 13 | GPT-5.4 Mini | 5.62 | #228 |
| 14 | Qwen 2.5 72B Instruct | 5.58 | #469 |
| 15 | Claude Opus 4.5 | 5.55 | #87 |
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-feasibility · How It Works · Data refreshed daily, snapshot 2026-11-05.