SupChain-Bench (Tool Calling) - Level 1: leaderboard
Metric: Information retrieval accuracy (%) on the 22 Level 1 questions (under 15 tool-execution steps) of SupChain-Bench's order-diagnosis tool-calling questions; the model sees only the question and the tool schemas; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 54.5 | #91 |
| 2 | Claude Sonnet 4 | 31.8 | #194 |
| 3 | Gemini 2.5 Pro | 18.2 | #145 |
| 4 | DeepSeek V3 | 18.2 | #312 |
| 5 | Kimi K2 | 18.2 | #236 |
| 6 | Qwen 3 Max | 4.5 | #201 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=supchain-bench-tool-calling-level-1 · How It Works · Data refreshed daily, snapshot 2026-10-11.