Combined Model Ranking

See which AI models perform best on Combined, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↑.

Models Shown

Average Combined Score

5.8

Best Model

Dots 3 Note Preview 6.9

Failure Reasons

With failure reason Invalid tool call147 With failure reason Wrong answer95 With failure reason No answer43 With failure reason API error37 With failure reason Timed out9 With failure reason Did not follow instructions1 With failure reason Extra formatting1

311/311

Rank	Model	Company	Combined Score	Score	Total Cost	Tests Correct	Response Time (avg)
#141	Step 3.7 Flash high	Stepfun	8.7	6.8	$1.229	1/2	41.2s
Total Tests 2 Wrong Tests 1 Total Cost $1.229 Response Time (avg) 41.2s
#116	Kimi K2.6 medium	Moonshot AI	6.9	7.2	$1.247	1/2	458.6s
Total Tests 2 Wrong Tests 1 Total Cost $1.247 Response Time (avg) 458.6s
#11	GPT-5.5 low	OpenAI	10.0	9.3	$1.257	2/2	13.7s
Total Tests 2 Wrong Tests 0 Total Cost $1.257 Response Time (avg) 13.7s
#138	Seed-2.0-Code high	Bytedance Seed	7.3	6.9	$1.273	1/2	144.9s
Total Tests 2 Wrong Tests 1 Total Cost $1.273 Response Time (avg) 144.9s
#37	Muse Spark 1.2 medium	Meta	8.5	8.6	$1.339	1/2	24.9s
Total Tests 2 Wrong Tests 1 Total Cost $1.339 Response Time (avg) 24.9s
#13	Gemini 3.1 Pro Preview medium	Google	9.8	9.2	$1.352	2/2	40.4s
Total Tests 2 Wrong Tests 0 Total Cost $1.352 Response Time (avg) 40.4s
#38	Muse Spark 1.1 medium	Meta	8.3	8.6	$1.420	1/2	42.6s
Total Tests 2 Wrong Tests 1 Total Cost $1.420 Response Time (avg) 42.6s
#29	Muse Spark 1.3 medium	Meta	7.3	8.8	$1.469	1/2	34.7s
Total Tests 2 Wrong Tests 1 Total Cost $1.469 Response Time (avg) 34.7s
#35	Claude Opus 4.7 medium	Anthropic	10.0	8.7	$1.476	2/2	43.4s
Total Tests 2 Wrong Tests 0 Total Cost $1.476 Response Time (avg) 43.4s
#18	Seed 2.1 Turbo low	Bytedance Seed	10.0	9.1	$1.546	2/2	360.0s
Total Tests 2 Wrong Tests 0 Total Cost $1.546 Response Time (avg) 360.0s
#89	Claude Opus 5 none	Anthropic	8.3	7.5	$1.550	1/2	30.5s
Total Tests 2 Wrong Tests 1 Total Cost $1.550 Response Time (avg) 30.5s
#42	GPT-5.4 medium	OpenAI	10.0	8.5	$1.560	2/2	29.8s
Total Tests 2 Wrong Tests 0 Total Cost $1.560 Response Time (avg) 29.8s
#16	Claude Opus 5 medium	Anthropic	10.0	9.2	$1.586	2/2	23.9s
Total Tests 2 Wrong Tests 0 Total Cost $1.586 Response Time (avg) 23.9s
#2	Gemini 3.8 Flash high	Google	10.0	9.9	$1.595	2/2	115.7s
Total Tests 2 Wrong Tests 0 Total Cost $1.595 Response Time (avg) 115.7s
#26	Muse Spark 1.3 high	Meta	10.0	8.9	$1.653	2/2	55.5s
Total Tests 2 Wrong Tests 0 Total Cost $1.653 Response Time (avg) 55.5s

Combined Ranking

Filter models

Top Models by Combined Score

Combined Score vs Total Cost

Top Models by Response Time (avg)