Tool Calling Model Ranking

AI BENCHY Category

See which AI models perform best on Tool Calling, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↓.

Models Shown

Average Tool Calling Score

8.7

Best Model

Failure Reasons

With failure reason API error6 With failure reason Did not follow instructions6 With failure reason Invalid tool call3 With failure reason No answer2 With failure reason Wrong answer2

Rank	Model	Company	Tool Calling Score	Score	Tests Correct	Response Time (avg)
#1	Gemini 3 Flash Preview medium	Google	10.0	10.0	1/1	10.6s
#2	Gemini 3.1 Pro Preview medium	Google	10.0	9.6	1/1	23.1s
#3	Claude Opus 4.7 medium	Anthropic	10.0	9.2	1/1	4.17s
#4	Claude Opus 4.7 none	Anthropic	10.0	9.2	1/1	4.74s
#5	Gemini 3 Flash Preview low	Google	10.0	8.8	1/1	4.99s
#6	Seed-2.0-Lite medium	Bytedance Seed	10.0	8.6	1/1	12.4s
#7	GPT-5.3-Codex medium	OpenAI	10.0	8.6	1/1	6.37s
#8	Qwen3.5 Plus 2026-02-15 medium	Qwen	10.0	8.5	1/1	7.54s
#9	Qwen3.6 Plus Preview medium	Qwen	10.0	8.5	1/1	5.87s
#10	Qwen3.5-27B medium	Qwen	10.0	8.4	1/1	7.45s
#11	Gemini 3.1 Flash Lite Preview high	Google	10.0	8.4	1/1	7.73s
#12	Gemini 3 PRO Preview medium	Google	10.0	8.4	1/1	12.0s
#13	GLM 5 medium	Z.ai	10.0	8.4	1/1	15.9s
#15	Gemini 2.5 Flash medium	Google	10.0	8.2	1/1	6.20s
#16	GPT-5.4 medium	OpenAI	10.0	8.2	1/1	13.3s

1 2 3 4 5 6 7

→

Tool Calling Ranking