Skip to content
Model Pulse

Leaderboard

Artificial Analysis Coding Indexofficial site ↗

27 models scored · metric: index. Prices are the cheapest listed across all serving providers. Cost/run and Pts/$ are priced for the chat token profile — short turns, light history, little caching — an assistant in a product.

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: 1.5k in · 500 out · 20% cache hit · 8k 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 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 · chat profile
  1. 1.Step 3.5 Flash 2603122,046
  2. 2.Step 3.5 Flash116,713
  3. 3.Qwen3-Coder 30B-A3B Instruct93,663
  4. 4.GLM-4.5-Air58,405
  5. 5.Llama-3.3-70B-Instruct57,450
27 models
#
🥇GPT-5-Codexopenai
38.9
$1.07$8.500.565¢6,889400K
🥈Step 3.7 Flashstepfun
37.1
$0.185$1.110.080¢46,261262K
🥉Step 3.5 Flash 2603stepfun
34.6
$0.1$0.30.028¢122,046262K
4North Mini Codecohere
33.4
————256K
5Gemini 2.5 Progoogle
32
$0.87$70.464¢6,9031.07M
6Step 3.5 Flashstepfun
31.6
$0.09$0.30.027¢116,713262K
7GLM-4.6zhipuai
29.5
$0.286$1.140.102¢28,881205K
8Qwen3 Maxalibaba
26.4
$0.36$1.430.120¢22,081262K
9GLM-4.5zhipuai
26.3
$0.286$1.140.102¢25,748131K
10Mistral Small 4mistral
24.3
$0.143$0.5680.047¢51,644262K
11GPT-4o (2024-05-13)openai
24.2
$5$15$0.0151,574128K
12GLM-4.5-Airzhipuai
23.8
$0.1$0.50.041¢58,405131K
13Devstral 2mistral
23.7
$0.4$20.152¢15,572262K
14Mistral Large 3mistral
22.7
$0.5$1.500.140¢16,185262K
15Gemini 2.5 Flashgoogle
22.2
$0.09$0.710.050¢44,6901.07M
16GPT-4 Turboopenai
21.5
$9$27$0.028777128K
17Qwen3-Coder 30B-A3B Instructalibaba
19.4
$0.06$0.250.021¢93,663262K
18GPT-4o (2024-11-20)openai
16.7
$2.50$100.856¢1,950128K
19GPT-4o (2024-08-06)openai
16.6
$2.50$100.856¢1,939128K
20DeepSeek-R1deepseek
15.9
$0.4$1.700.142¢11,197164K
1–20 of 27 models

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

Cheapest scorer: Llama-3.3-70B-Instruct at $0.05 input /M.