Cost-performance analysis
Which Model Is Best for Coding?
A cost-performance leaderboard of the models coding agents run on - benchmark scores, real token-mix pricing, latency, and decoding speed.
Models used by coding agents
Sort by:
GPT-5.5 OpenAI#1DF Score 89.3Price / 1M out $216Latency 118.46sContext window 1.05M
Gemini 3.5 Flash Google#2DF Score 85.0Price / 1M out $62.0Latency 20.59sContext window 1M
Claude Fable 5 (with fallback) Anthropic#3DF Score 80.3Price / 1M out $343Latency 239.01sContext window 1M- GPT-5.4 OpenAI#4DF Score 79.2Price / 1M out $85.5Latency 113.80sContext window 1M
- Gemini 3.1 Pro (Preview) Google#5DF Score 77.4Price / 1M out $73.6Latency 25.74sContext window 1M
- Claude Opus 4.7 Anthropic#6DF Score 74.5Price / 1M out $140Latency —Context window 1M
- Claude Sonnet 5 Anthropic#7DF Score 71.3Price / 1M out $115Latency 144.37sContext window 1M
- Claude Opus 4.8 Anthropic#8DF Score 69.6Price / 1M out $136Latency 30.05sContext window 1M
- GPT-5.4 mini OpenAI#9DF Score 63.0Price / 1M out $16.0Latency 11.87sContext window 400k
- GPT-5.3 Codex OpenAI#10DF Score 62.4Price / 1M out $70.5Latency 79.89sContext window 400k
- Gemini 3 Flash (Preview) Google#11DF Score 57.2Price / 1M out $17.5Latency 7.60sContext window 1M
- GPT-5.4 nano OpenAI#12DF Score 55.8Price / 1M out $7.71Latency 4.74sContext window 400k
- Claude Sonnet 4.6 Anthropic#13DF Score 53.4Price / 1M out $98.1Latency 1.16sContext window 1M
- Kimi-K2.7-Code Moonshot AI#14DF Score 50.0Price / 1M out $41.8Latency 2.92sContext window 256k
- Claude Opus 4.6 Anthropic#15DF Score 45.7Price / 1M out $140Latency —Context window 1M
- Claude Opus 4.5 Anthropic#16DF Score 37.5Price / 1M out $140Latency 15.04sContext window 200k
- Claude Sonnet 4.5 Anthropic#17DF Score 34.7Price / 1M out $83.8Latency 1.36sContext window 1M
- Claude Haiku 4.5 Anthropic#18DF Score 30.5Price / 1M out $31.8Latency 0.81sContext window 200k
- GPT-5 mini OpenAI#19DF Score 26.9Price / 1M out $10.1Latency 85.30sContext window 400k
- GPT-OSS 120B OpenAI#20DF Score 16.2Price / 1M out $31.5Latency 0.94sContext window 131k
- Gemini 2.5 Pro Google#21DF Score 12.5Price / 1M out $48.5Latency 22.54sContext window 1M
- GPT-5.3 Codex Spark OpenAI#22DF Score —Price / 1M out —Latency —Context window
- Claude Opus 4.8 Fast Anthropic#23DF Score —Price / 1M out $280Latency —Context window 1M
- MAI-Code-1-Flash Microsoft#24DF Score —Price / 1M out $22.0Latency —Context window
- Raptor mini GitHub#25DF Score —Price / 1M out $7.85Latency —Context window 400k
Help us to detect updates in plans values
The prices and token mixes above are driven by real coding usage. Share yours via letmecode to allow us discover updates in plans values.
$ npx letmecode@latest