Data parsing and extraction x Extra formatting Ranking

See which AI models are most likely to hit Extra formatting on Data parsing and extraction, so you can spot weak points faster.

Models Shown

Total Failures

Most Affected Model

Failure Reasons

Wrong answer41 API error14 No answer8 Extra formatting6 Timed out1

Categories

Anti-AI Tricks20 Coding18 Domain specific17 Puzzle Solving8 Data parsing and extraction6 Instructions following3 Combined1

6/6

Rank	Model	Company	Extra formatting Count	Category Score	Total Cost	Tests Correct	Response Time (avg)
#33	Kimi K3 max	Moonshot AI	1	7.3	$3.112	1/2	16.7s
Total Tests 2 Wrong Tests 1 Total Cost $3.112 Response Time (avg) 16.7s
#101	MiMo-V2.5 medium	Xiaomi	1	2.7	$0.082	0/2	6.33s
Total Tests 2 Wrong Tests 2 Total Cost $0.082 Response Time (avg) 6.33s
#168	MiMo-V2.5 none	Xiaomi	1	6.5	$0.025	1/2	1.01s
Total Tests 2 Wrong Tests 1 Total Cost $0.025 Response Time (avg) 1.01s
#182	KAT-Coder-Air V2.5 none	Kwaipilot	1	6.3	$0.067	1/2	2.66s
Total Tests 2 Wrong Tests 1 Total Cost $0.067 Response Time (avg) 2.66s
#200	MiMo-V2-Flash none	Xiaomi	1	2.9	$0.025	0/2	19.7s
Total Tests 2 Wrong Tests 2 Total Cost $0.025 Response Time (avg) 19.7s
#204	Qwen3.5-9B medium	Qwen	1	3.6	$0.036	0/2	87.3s
Total Tests 2 Wrong Tests 2 Total Cost $0.036 Response Time (avg) 87.3s

Filter models