GroupTravelBench - LLM Judge: leaderboard
Metric: LLM-judge process score (0-100): mean of five 1-5 ratings (hallucination, tool-use reasoning, interaction, conflict coordination, plan humanization) rescaled to 0-100 and multiplied by a 1-5 meta-judge calibration over 5, Gemini-3-Flash-Preview judge and meta-judge at temperature 0, over all 650 tasks, on GroupTravelBench, multi-user multi-turn group travel planning in a group-chat sandbox with 10 cached travel tools (DeepSeek-V4-Flash user simulator at temperature 0, agent temperature 0.7, mean of 3 trials per task); GPT-5.1 in instruct mode, the other models with reasoning enabled; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 (Non-reasoning) | 85.2 |
| 2 | Qwen 3.5 Plus (Thinking) | 62.2 |
| 3 | Qwen 3.6 Max (Preview) (Thinking) | 57.3 |
| 4 | Qwen 3.5 Flash (Thinking) | 43.7 |
| 5 | Qwen 3 4B Instruct | 22.9 |
Interactive version: theaggregate.ai/benchmark?slug=grouptravelbench-llm-judge · How It Works · Data refreshed daily, snapshot 2026-10-07.