Crosby micro1 RedlineBench: leaderboard
Multi-turn contract-redlining benchmark for SaaS MSA negotiations, using document-native redlines, attorney-authored golden responses, and rubric-based turn-level and behavioral evaluation. (Source: benchmarklist.com, self-reported.)
Metric: Turn-weighted score (imported). Source: benchmarklist.com. Saturation forecast: Around February 2028. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 59.5 | #8 |
| 2 | Claude Opus 5 | 56.9 | #12 |
| 3 | GPT-5.6 Sol | 56.2 | #19 |
| 4 | GPT-5.6 Luna | 55.5 | #68 |
| 5 | Gemini 3.8 Flash | 55.2 | #21 |
| 6 | Claude Opus 5.5 | 53.5 | #3 |
| 7 | Gemini 3.6 Flash | 51 | #51 |
| 8 | GPT-5.5 | 50.5 | #31 |
| 9 | Kimi K3 | 49.3 | #30 |
| 10 | GPT-5.6 Terra | 49.3 | #41 |
| 11 | Claude Fable 5 | 47.3 | #16 |
| 12 | GLM-5.2 | 45.7 | #73 |
| 13 | Gemini 3.5 Flash | 45.1 | #60 |
| 14 | Claude Opus 4.8 | 44.4 | #37 |
No result here: #6 GPT-6 Astra, #7 GPT-6.1 Sol, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=crosby-micro1-redlinebench · How It Works · Data refreshed daily, snapshot 2026-10-20.