← Arena leaderboards

Tool Hallucination

Arena · 50 models

RankModelScore
1GLM-5.3-Flash0.008
2GPT-6 Astra (Max)0.008
3GLM-5.3 (Max)0.008
4DeepSeek-V4-Pro (High, 20260813)0.008
5GPT-6 Luna (Low)0.008
6GPT-6 Sol (Max)0.008
7Grok 4.6 (xHigh)0.008
8GPT-6.1 Terra (Max)0.008
9GPT-6 Luna (Medium)0.008
10Kimi K3.1 Pro (Max)0.008
11GPT-5.6 Sol (xHigh)0.008
12GPT-6.1 Sol (Max)0.008
13Kimi K3 (Max)0.008
14Grok 4.7 (xHigh)0.008
15GPT-6 Luna (Max)0.008
16GLM-5.2 (Max)0.008
17GPT-5.6 Terra (xHigh)0.0078
18Muse Spark 1.10.0076
19Muse Spark 1.3 (Max)0.0075
20Claude Opus 5 (Max)0.0075
21Claude Sonnet 5.5 (Max)0.0071
22Claude Fable 5.1 (Max)0.0068
23Muse Spark 1.2 (xHigh)0.0064
24Claude Opus 5.5 (Max)0.0054
25Gemini 4 Carbon (High)0.0053
26Claude Fable 5 (High)0.005
27Gemini 3.7 Flash (High)0.0049
28Claude Sonnet 5 (High)0.0048
29Gemini 4 Argon (High)0.0036
30DeepSeek-V4.1-Flash-20261017 (Max)0.0035
31Gemini 3.8 Flash (High)0.0034
32MiniMax-M3.1-Flash0.0014
33Hy4 preview0.0011
34Step 5 Preview0.0001
35Qwen3.8-27B-0.0001
36Gemini 3.1 Pro Preview-0.0005
37MiMo-V2.6-Pro-0.0021
38Qwen3.7-Max-0.0039
39Muse Wonder Full (Max)-0.0045
40Qwen3.8-Max-0.0073
41Beam 1.0 501B A23B-0.0082
42Qwen3.8-Flash-Next-0.0082
43Muse Wonder (Max)-0.0091
44MiMo-V2.5-Pro-0.0105
45Claude Haiku 5.5 (High)-0.014
46MiniMax-M3-0.016
47Nemotron 3 Ultra-0.0167
48Spark-X2.6-0.0172
49Inkling-0.018
50Qwen3.7-Plus-0.0279