Data parsing and extraction Model Ranking

AI BENCHY Category

See which AI models perform best on Data parsing and extraction, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.

Models Shown

Average Data parsing and extraction Score

9.0

Best Model

Failure Reasons

With failure reason Wrong answer19 With failure reason API error6 With failure reason Extra formatting2 With failure reason No answer2 With failure reason Timed out1

Rank	Model	Company	Data parsing and extraction Score	Score	Tests Correct	Response Time (avg)
#84	gpt-oss-120b none	OpenAI	6.5	5.2	1/2	7.12s
#13	GLM 5 medium	Z.ai	7.1	8.4	1/2	8.90s
#23	MiMo-V2-Pro medium	Xiaomi	7.3	8.1	1/2	17.2s
#74	GLM 4.7 Flash none	Z.ai	7.3	5.6	1/2	4.82s
#76	Kimi K2.5 none	Moonshot AI	7.3	5.5	1/2	42.1s
#32	Qwen3.5-Flash medium	Qwen	7.3	7.8	1/2	57.0s
#43	Qwen3.5-35B-A3B medium	Qwen	7.3	7.4	1/2	59.3s
#54	Mercury 2 medium	Inception	7.3	6.5	1/2	1.11s
#73	Mistral Small 4 medium	Mistral	7.3	5.7	1/2	1.23s
#91	Mercury 2 none	Inception	7.3	4.8	1/2	667ms
#1	Gemini 3 Flash Preview medium	Google	10.0	10.0	2/2	4.72s
#2	Gemini 3.1 Pro Preview medium	Google	10.0	9.6	2/2	7.72s
#3	Claude Opus 4.7 medium	Anthropic	10.0	9.2	2/2	2.37s
#4	Claude Opus 4.7 none	Anthropic	10.0	9.2	2/2	2.15s
#5	Gemini 3 Flash Preview low	Google	10.0	8.8	2/2	9.40s

←

1 2 3 4 5 6 7

→

Data parsing and extraction Ranking