Skip to content
Model Pulse

Leaderboard

Artificial Analysis Coding Agent Indexofficial site ↗

13 models scored · metric: average pass@1. Prices are the cheapest listed across all serving providers. Cost/run and Pts/$ are priced for the agentic token profile — tool loops re-send a growing transcript and think between calls.

A benchmark is priced for the workload it exercises, not a fixed input:output blend: an agent loop and a single hard question bill very differently on the same rate card. Profile: 12k in · 2k out · 3k reasoning · 70% cache hit · 32k context.

Scores are facts as publicly reported by labs (see report links below and on each model page) and aggregated via models.dev. Artificial Analysis Coding Agent Index is maintained by its own project — Model Pulse is not affiliated with or endorsed by it.

Best value · top 5 by pts per dollar · agentic profile
  1. 1.GPT-5.6 Luna27,857
  2. 2.DeepSeek V4 Pro8,470
  3. 3.GPT-5.57,951
  4. 4.Kimi K2.65,433
  5. 5.GLM-5.14,041
13 models
#
🥇GPT-5.6 Solopenai
80
$2$10$0.0631,2621.05M
🥈GPT-5.6 Terraopenai
77.4
$1.50$2$0.0193,9981.05M
🥉GPT-5.6 Lunaopenai
74.6
$0.06$0.370.268¢27,8571.05M
4GPT-6 Astraopenai
67
$10$50$0.3122141.05M
5Claude Opus 4.7anthropic
66.6
$4$20$0.0679981.05M
6GPT-5.5openai
65.3
$0.188$1.130.821¢7,9511.05M
7GPT-5.4openai
53.6
$0.75$6$0.0351,5461.05M
8GLM-5.1zhipuai
52.7
$0.45$2.15$0.0134,041205K
9Claude Opus 4.6anthropic
51.3
$4$20$0.0677681M
10Kimi K2.6moonshotai
50.5
$0.275$1.100.930¢5,433262K
11DeepSeek V4 Prodeepseek
50.1
$0.35$0.80.592¢8,4701.05M
12Claude Sonnet 4.6anthropic
49.4
$0.9$5.55$0.0331,4811M
13Gemini 3.1 Pro Previewgoogle
43
$1$6$0.0351,2361.05M
1–13 of 13 models

Score reports: artificialanalysis.ai · artificialanalysis.ai · artificialanalysis.ai — full source URLs are linked on each model page.

Cheapest scorer: GPT-5.6 Luna at $0.06 input /M.