RobustBench-TC - Clean: leaderboard

RobustBench-TC (2026) tests tool-calling models under deployment noise grounded in real tool-calling failures, using 199 single-turn samples drawn from BFCL, API-Bank, RoTBench, ToolAlpaca and ToolEyes and scored by deterministic rule-based parsers. This board is tool-call accuracy in percent on the unperturbed reference samples; higher is better.

Metric: Tool-call accuracy (%) on the 199 unperturbed baseline samples of RobustBench-TC, the clean reference for its perturbations; RobustBench-TC samples drawn from BFCL V3 single-turn, API-Bank, RoTBench, ToolAlpaca and ToolEyes, each scored by its source benchmark's strict scorer after a format-tolerant tool-call parse, temperature 0 (DeepSeek-R1-Distill at 0.6), Qwen3-family models with thinking disabled; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 18 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1LoopTool-32B77.9
2Qwen 3 32BNon-reasoning75.4#983
3Qwen 3 14BNon-reasoning74.9#1284
4LoopTool-8B71.4#1497
5O4 Mini70.9#372
6Qwen 3.5 9BNon-reasoning70.9#838
7ToolRL-Qwen2.5-1.5B70.4#2330
8MUA-RL-32B68.3
9MUA-RL-8B67.8#1656
10Qwen 3 8BNon-reasoning67.3#1890
11TL-CodeLLaMA-265.3
12ToolRL-Qwen2.5-3B63.8
13MUA-RL-14B62.8#1674
14ToolRL-Llama3.2-3B62.8
15DeepSeek R1 Distill Qwen 14B61.8#2739

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Example tasks

How much traffic should I expect from Las Vegas to Los Angeles this weekend?

Source

What is the area of a rectangle with length 12 meters and width 5 meters?

Source

Interactive version: theaggregate.ai/benchmark?slug=robustbench-tc-clean · How It Works · Data refreshed daily, snapshot 2026-11-22.