GroupTravelBench - LLM Judge: leaderboard
GroupTravelBench LLM Judge rates the planning process of an LLM agent in group travel chats on hallucination, tool-use reasoning, interaction, conflict coordination and plan humanization, with a Gemini 3 Flash judge calibrated by a meta-judge (GroupTravelBench, 2026). The score runs from 0 to 100, higher is better.
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 February 2027. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | DeepSeek V4 Pro | Thinking | 92.3 | #196 |
| 2 | GPT-5.1 | Non-reasoning | 85.2 | #240 |
| 3 | Qwen 3.5 Plus | Thinking | 62.2 | #242 |
| 4 | Qwen 3.6 Max (Preview) | Thinking | 57.3 | |
| 5 | GroupTravelBench Qwen3-235B-A22B-Thinking (checkpoint unspecified) | 45.4 | ||
| 6 | Qwen 3.5 Flash | Thinking | 43.7 | #441 |
| 7 | GroupTravelBench Qwen3-4B-Thinking (checkpoint unspecified) | 24.8 | ||
| 8 | Qwen 3 4B Instruct | 22.9 | #1696 | |
| 9 | GroupTravelBench Qwen3-30B-A3B-Thinking (checkpoint unspecified) | 21.3 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=grouptravelbench-llm-judge · How It Works · Data refreshed daily, snapshot 2026-11-21.