RobustBench-TC - Duplicate Tool With Description: 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 under an injected same-name distractor tool with the correct description but no parameters; higher is better.

Metric: Tool-call accuracy (%) under the Dup-Desc perturbation (action component: same name; correct description, no params); 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
1MUA-RL-32B74
2Qwen 3 32BNon-reasoning64.6#983
3Qwen 3 14BNon-reasoning63#1284
4LoopTool-32B62.2
5O4 Mini55.9#372
6Qwen 3.5 9BNon-reasoning52.8#838
7LoopTool-8B52#1497
8MUA-RL-8B51.2#1656
9MUA-RL-14B50.4#1674
10ToolRL-Qwen2.5-3B48.8
11Qwen 3 8BNon-reasoning47.2#1890
12DeepSeek R1 Distill Qwen 14B46.5#2739
13ToolRL-Qwen2.5-1.5B46.5#2330
14TL-CodeLLaMA-244.1
15ToolRL-Llama3.2-3B44.1

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

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