TERMS-Bench — leaderboard
Negotiation benchmark for LLM agents bargaining over terms under changing utility, urgency, and no-deal regimes, reporting mean utility and agreement metrics.
Metric: Mean Utility. Source: terms-bench.github.io. Status: saturation imminent. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.1 | 11.7 |
| 2 | Claude Opus 4.6 | 11.62 |
| 3 | Claude Opus 4.7 | 11.09 |
| 4 | Gemma 4 31B | 10.64 |
| 5 | Gemini 3.1 Pro (Preview) | 10.58 |
| 6 | DeepSeek V4 Pro | 10.53 |
| 7 | Qwen 3.6 Plus | 10.3 |
| 8 | Kimi K2.6 | 10.17 |
| 9 | GPT-5.5 | 10.15 |
| 10 | Grok 4.20 | 10.03 |
| 11 | Seed 2.0 Pro | 8.61 |
| 12 | GPT-4o Mini | 3.37 |
Interactive version: theaggregate.ai/benchmark?slug=terms-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.