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-5.6 Sol OpenAI#1DF Score 87.4Avg task cost $0.486Latency —Context window 1.05M- GPT-5.5 OpenAI#2DF Score 85.0Avg task cost $0.490Latency 118.46sContext window 1.05M
- GPT-5.6 Terra OpenAI#3DF Score 83.5Avg task cost $0.293Latency —Context window 1.05M
Claude Opus 5 Anthropic#4DF Score 81.3Avg task cost $0.565Latency 56.78sContext window 1M'%3e%3c/path%3e%3cpath%20d='M20.616%2010.835a14.147%2014.147%200%2001-4.45-3.001%2014.111%2014.111%200%2001-3.678-6.452.503.503%200%2000-.975%200%2014.134%2014.134%200%2001-3.679%206.452%2014.155%2014.155%200%2001-4.45%203.001c-.65.28-1.318.505-2.002.678a.502.502%200%20000%20.975c.684.172%201.35.397%202.002.677a14.147%2014.147%200%20014.45%203.001%2014.112%2014.112%200%20013.679%206.453.502.502%200%2000.975%200c.172-.685.397-1.351.677-2.003a14.145%2014.145%200%20013.001-4.45%2014.113%2014.113%200%20016.453-3.678.503.503%200%20000-.975%2013.245%2013.245%200%2001-2.003-.678z'%20fill='url(%23lobe-icons-gemini-1-_R_0_)'%3e%3c/path%3e%3cpath%20d='M20.616%2010.835a14.147%2014.147%200%2001-4.45-3.001%2014.111%2014.111%200%2001-3.678-6.452.503.503%200%2000-.975%200%2014.134%2014.134%200%2001-3.679%206.452%2014.155%2014.155%200%2001-4.45%203.001c-.65.28-1.318.505-2.002.678a.502.502%200%20000%20.975c.684.172%201.35.397%202.002.677a14.147%2014.147%200%20014.45%203.001%2014.112%2014.112%200%20013.679%206.453.502.502%200%2000.975%200c.172-.685.397-1.351.677-2.003a14.145%2014.145%200%20013.001-4.45%2014.113%2014.113%200%20016.453-3.678.503.503%200%20000-.975%2013.245%2013.245%200%2001-2.003-.678z'%20fill='url(%23lobe-icons-gemini-2-_R_0_)'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-gemini-0-_R_0_'%20x1='7'%20x2='11'%20y1='15.5'%20y2='12'%3e%3cstop%20stop-color='%2308B962'%3e%3c/stop%3e%3cstop%20offset='1'%20stop-color='%2308B962'%20stop-opacity='0'%3e%3c/stop%3e%3c/linearGradient%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-gemini-1-_R_0_'%20x1='8'%20x2='11.5'%20y1='5.5'%20y2='11'%3e%3cstop%20stop-color='%23F94543'%3e%3c/stop%3e%3cstop%20offset='1'%20stop-color='%23F94543'%20stop-opacity='0'%3e%3c/stop%3e%3c/linearGradient%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-gemini-2-_R_0_'%20x1='3.5'%20x2='17.5'%20y1='13.5'%20y2='12'%3e%3cstop%20stop-color='%23FABC12'%3e%3c/stop%3e%3cstop%20offset='.46'%20stop-color='%23FABC12'%20stop-opacity='0'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
Gemini 3.5 Flash Google#5DF Score 81.3Avg task cost $0.620Latency 20.59sContext window 1M- Claude Fable 5 Anthropic#6DF Score 78.5Avg task cost $2.36Latency 239.01sContext window 1M
- GPT-5.4 OpenAI#7DF Score 75.9Avg task cost $0.254Latency 113.80sContext window 1M
- Gemini 3.1 Pro (Preview) Google#8DF Score 74.5Avg task cost $0.783Latency 25.74sContext window 1M
- GPT-5.6 Luna OpenAI#9DF Score 70.9Avg task cost $0.151Latency —Context window 1.05M
- Claude Opus 4.7 Anthropic#10DF Score 69.4Avg task cost $1.58Latency —Context window 1M
- Claude Sonnet 5 Anthropic#11DF Score 69.2Avg task cost $0.969Latency 144.37sContext window 1M
- Claude Opus 4.8 Anthropic#12DF Score 67.8Avg task cost $1.16Latency 30.05sContext window 1M
- GPT-5.3 Codex OpenAI#13DF Score 61.9Avg task cost —Latency 79.89sContext window 400k
- GPT-5.4 mini OpenAI#14DF Score 59.9Avg task cost $0.183Latency 11.87sContext window 400k
- Gemini 3 Flash (Preview) Google#15DF Score 57.0Avg task cost —Latency 7.60sContext window 1M
- GPT-5.4 nano OpenAI#16DF Score 53.6Avg task cost —Latency 4.74sContext window 400k
- Claude Sonnet 4.6 Anthropic#17DF Score 50.0Avg task cost —Latency 1.16sContext window 1M
- Kimi-K2.7-Code Moonshot AI#18DF Score 48.8Avg task cost —Latency 2.92sContext window 256k
- Claude Opus 4.6 Anthropic#19DF Score 45.4Avg task cost $0.581Latency —Context window 1M
- Claude Opus 4.5 Anthropic#20DF Score 37.2Avg task cost —Latency 15.04sContext window 200k
- Claude Sonnet 4.5 Anthropic#21DF Score 33.8Avg task cost —Latency 1.36sContext window 1M
- Claude Haiku 4.5 Anthropic#22DF Score 28.0Avg task cost $0.159Latency 0.81sContext window 200k
- GPT-5 mini OpenAI#23DF Score 26.8Avg task cost —Latency 85.30sContext window 400k
- GPT-OSS 120B OpenAI#24DF Score 15.9Avg task cost —Latency 0.94sContext window 131k
- Gemini 2.5 Pro Google#25DF Score 12.1Avg task cost —Latency 22.54sContext window 1M
- GPT-5.3 Codex Spark OpenAI#26DF Score —Avg task cost —Latency —Context window
- Claude Opus 4.8 Fast Anthropic#27DF Score —Avg task cost —Latency —Context window 1M
- MAI-Code-1-Flash Microsoft#28DF Score —Avg task cost —Latency —Context window
- Raptor mini GitHub#29DF Score —Avg task cost —Latency —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
FAQ
'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-codex-_R_0_'%20x1='12'%20x2='12'%20y1='3'%20y2='21'%3e%3cstop%20stop-color='%23B1A7FF'%3e%3c/stop%3e%3cstop%20offset='.5'%20stop-color='%237A9DFF'%3e%3c/stop%3e%3cstop%20offset='1'%20stop-color='%233941FF'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
Something unclear or missing?
If any of the numbers or terms above don't add up, or you spotted something that looks off, tell us - we'll clarify and keep the data sharper for everyone.
Report inconsistency