Data parsing and extraction Model Ranking

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

Models Shown

Average Data parsing and extraction Score

8.8

Best Model

Gemini 3.6 Flash 10.0

Failure Reasons

With failure reason Wrong answer67 With failure reason API error31 With failure reason Extra formatting10 With failure reason No answer9 With failure reason Did not follow instructions8 With failure reason Timed out2

359/359

Rank	Model	Company	Data parsing and extraction Score	Score	Total Cost	Tests Correct	Response Time (avg)
#65	Qwen3.8 27B high	Qwen	10.0	8.4	~$0.287	2/2	34.9s
Total Tests 2 Wrong Tests 0 Total Cost ~$0.287 Response Time (avg) 34.9s
#66	MiMo-V2.6-Pro medium	Xiaomi	10.0	8.4	$0.477	2/2	2.71s
Total Tests 2 Wrong Tests 0 Total Cost $0.477 Response Time (avg) 2.71s
#67	Seed 2.1 Turbo medium	Bytedance Seed	10.0	8.4	$1.951	2/2	37.8s
Total Tests 2 Wrong Tests 0 Total Cost $1.951 Response Time (avg) 37.8s
#68	GPT-6 Sol low	OpenAI	10.0	8.4	$0.273	2/2	13.6s
Total Tests 2 Wrong Tests 0 Total Cost $0.273 Response Time (avg) 13.6s
#69	Inkling Small high	Thinkingmachines	10.0	8.4	$0.398	2/2	3.99s
Total Tests 2 Wrong Tests 0 Total Cost $0.398 Response Time (avg) 3.99s
#70	GLM 5.3 FlashX max	Z.ai	10.0	8.3	$0.508	2/2	3.38s
Total Tests 2 Wrong Tests 0 Total Cost $0.508 Response Time (avg) 3.38s
#72	Muse Spark 1.1 low	Meta	10.0	8.3	$0.673	2/2	3.22s
Total Tests 2 Wrong Tests 0 Total Cost $0.673 Response Time (avg) 3.22s
#73	GPT-6 Luna high	OpenAI	10.0	8.3	$0.054	2/2	24.5s
Total Tests 2 Wrong Tests 0 Total Cost $0.054 Response Time (avg) 24.5s
#74	Claude Fable 5.1 medium	Anthropic	10.0	8.3	$2.909	2/2	4.47s
Total Tests 2 Wrong Tests 0 Total Cost $2.909 Response Time (avg) 4.47s
#75	Gemini 2.5 Flash medium	Google	10.0	8.2	$0.644	2/2	4.06s
Total Tests 2 Wrong Tests 0 Total Cost $0.644 Response Time (avg) 4.06s
#76	Muse Spark 1.3 low	Meta	10.0	8.2	$0.689	2/2	3.62s
Total Tests 2 Wrong Tests 0 Total Cost $0.689 Response Time (avg) 3.62s
#77	Claude Sonnet 5 medium	Anthropic	10.0	8.2	$0.922	2/2	3.16s
Total Tests 2 Wrong Tests 0 Total Cost $0.922 Response Time (avg) 3.16s
#78	Qwen3.8 2.4T A95B low	Qwen	10.0	8.1	$2.672	2/2	22.3s
Total Tests 2 Wrong Tests 0 Total Cost $2.672 Response Time (avg) 22.3s
#79	GPT-5 Mini medium	OpenAI	10.0	8.1	$0.241	2/2	12.6s
Total Tests 2 Wrong Tests 0 Total Cost $0.241 Response Time (avg) 12.6s
#80	Muse Glimmer 30B xhigh	Meta	10.0	8.1	$0.510	2/2	19.8s
Total Tests 2 Wrong Tests 0 Total Cost $0.510 Response Time (avg) 19.8s

Data parsing and extraction Ranking

Filter models

Top Models by Data parsing and extraction Score

Data parsing and extraction Score vs Total Cost

Top Models by Response Time (avg)

Data parsing and extraction Ranking

Filter models

Top Models by Data parsing and extraction Score

Data parsing and extraction Score vs Total CostEstimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 2.8999 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.286715.

Top Models by Response Time (avg)

Data parsing and extraction Score vs Total Cost