Coding Model Ranking

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

Models Shown

Average Coding Score

0.6

Best Model

GLM 5.1 0.5

Failure Reasons

With failure reason Wrong answer456 With failure reason API error64 With failure reason Did not follow instructions41 With failure reason No answer41 With failure reason Extra formatting36 With failure reason Timed out24

404/404

Rank	Model	Company	Coding Score	Score	Total Cost	Tests Correct	Response Time (avg)
#333	Mercury 2.5 Preview default	Inception	0.5	0.5	$0.023	0/3	459ms
Total Tests 3 Wrong Tests 3 Total Cost $0.023 Response Time (avg) 459ms
#334	Nemotron 3.5 Lightning medium	NVIDIA	0.4	0.5	$0.195	0/3	285.5s
Total Tests 3 Wrong Tests 3 Total Cost $0.195 Response Time (avg) 285.5s
#335	North Mini Code default	Cohere	0.4	0.5	$0.000	0/3	22.0s
Total Tests 3 Wrong Tests 3 Total Cost $0.000 Response Time (avg) 22.0s
#336	Laguna S 2.1 none	Poolside	0.3	0.5	$0.044	0/3	550ms
Total Tests 3 Wrong Tests 3 Total Cost $0.044 Response Time (avg) 550ms
#337	Granite 4.2 8B high	IBM Granite	0.4	0.5	$0.111	0/3	515.3s
Total Tests 3 Wrong Tests 3 Total Cost $0.111 Response Time (avg) 515.3s
#338	Qwen3 Coder Next medium	Qwen	0.4	0.5	$0.071	0/3	924ms
Total Tests 3 Wrong Tests 3 Total Cost $0.071 Response Time (avg) 924ms
#339	DeepSeek V3.2 none	DeepSeek	0.3	0.5	$0.119	0/3	14.5s
Total Tests 3 Wrong Tests 3 Total Cost $0.119 Response Time (avg) 14.5s
#340	GPT-5.4 Nano none	OpenAI	0.5	0.5	$0.068	0/3	2.22s
Total Tests 3 Wrong Tests 3 Total Cost $0.068 Response Time (avg) 2.22s
#343	Laguna S 2.1 low	Poolside	0.4	0.5	$0.108	0/3	167.5s
Total Tests 3 Wrong Tests 3 Total Cost $0.108 Response Time (avg) 167.5s
#344	Nemotron 3.5 Lightning low	NVIDIA	0.4	0.5	$0.175	0/3	224.4s
Total Tests 3 Wrong Tests 3 Total Cost $0.175 Response Time (avg) 224.4s
#351	Mimo V2 Omni default	Xiaomi	0.4	0.4	$0.021	0/3	2.75s
Total Tests 3 Wrong Tests 3 Total Cost $0.021 Response Time (avg) 2.75s
#352	Nemotron 3 Super none	NVIDIA	0.3	0.4	$0.016	0/3	2.64s
Total Tests 3 Wrong Tests 3 Total Cost $0.016 Response Time (avg) 2.64s
#353	KAT Coder AIR V2.5 default	Kwaipilot	0.3	0.4	$0.070	0/3	14.3s
Total Tests 3 Wrong Tests 3 Total Cost $0.070 Response Time (avg) 14.3s
#354	Trinity Large Preview default	Arcee AI	0.4	0.4	$0.008	0/3	14.3s
Total Tests 3 Wrong Tests 3 Total Cost $0.008 Response Time (avg) 14.3s
#356	Cobuddy medium	Baidu	0.4	0.4	$0.000	0/3	79.2s
Total Tests 3 Wrong Tests 3 Total Cost $0.000 Response Time (avg) 79.2s

Coding Ranking

Filter models

Top Models by Coding Score

Coding Score vs Total Cost

Top Models by Response Time (avg)