WildToolBench - Multi-Tool Tasks: leaderboard
WildToolBench (2026) evaluates LLM tool use under realistic user behavior: 256 multi-turn scenarios over about 1,600 public APIs mix compositional tool orchestration, intentions hidden in earlier turns and switches between tool, chat and clarification requests. This board is accuracy in percent on compositional tasks that need several sequential or parallel tool calls; higher is better.
Metric: Accuracy (%) on compositional tasks needing multi-step sequential or parallel tool calls, on WildToolBench (256 multi-turn scenarios, four user tasks each, 1,024 tasks, built from real user-log patterns with expert-annotated tool calls), each model through its native function-call format with default decoding; higher is better. Source: arxiv.org. Saturation forecast: Around November 2027. 50 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 44.14 | #505 |
| 2 | Claude Sonnet 4 | 43.75 | #410 |
| 3 | GPT-4o | 41.8 | #751 |
| 4 | Grok 4 | 41.41 | #319 |
| 5 | DeepSeek R1 | 41.02 | #482 |
| 6 | DeepSeek V3.1 | 40.63 | #511 |
| 7 | GLM-4.5 | 40.63 | #542 |
| 8 | Seed-1.6 | 40.23 | #469 |
| 9 | Gemini 2.0 Flash (Thinking) | 40.23 | |
| 10 | Claude Opus 4.1 | 39.84 | #278 |
| 11 | O3 | 39.45 | #237 |
| 12 | Claude 3.7 Sonnet | 39.06 | #470 |
| 13 | O1 | 39.06 | #403 |
| 14 | DeepSeek V3 | 38.67 | #729 |
| 15 | Qwen 2.5 32B Instruct | 38.67 | #1247 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=wildtoolbench-multi-tool-tasks · How It Works · Data refreshed daily, snapshot 2026-11-21.