ClawArena-Team - Tool-Permission Precision: leaderboard
ClawArena-Team (2026) measures how well one language model manages a team of subagents: over 41 multi-turn multimodal scenarios, a text-only main agent must create, empower and schedule a fixed local pool of text, vision and audio subagents, with execution-based checks and no LLM judge. The board is tool-permission precision, the share of the tool types granted to each subagent that it actually uses, in percent; higher is better.
Metric: Tool-permission precision (%): per subagent, the share of granted tool types actually used, averaged; 41 multi-turn multimodal scenarios with 258 evaluation rounds; a text-only main agent with partial workspace access creates, empowers and schedules a fixed locally served pool of LLM, VLM and omni subagents; execution-based checks, no LLM judge; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 79.9 | #49 |
| 2 | Gemma 4 31B | 79 | #394 |
| 3 | Claude Sonnet 4.6 | 77.3 | #161 |
| 4 | GPT-5.4 | 77.3 | #123 |
| 5 | Kimi K2.6 | 76.8 | #178 |
| 6 | Gemini 3.1 Pro (Preview) | 76.4 | #94 |
| 7 | Claude Fable 5 | 76.4 | #27 |
| 8 | DeepSeek V4 Pro | 73.9 | #188 |
| 9 | Qwen 3.6 27B | 72.5 | #341 |
| 10 | Gemini 3.5 Flash | 69.8 | #101 |
| 11 | GLM-5.2 | 67.4 | #138 |
| 12 | GLM-4.7 Flash | 22.4 | #1259 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=clawarena-team-tool-permission-precision · How It Works · Data refreshed daily, snapshot 2026-11-13.