Best AI models for coding
Ranked by a 0–100 composite of coding benchmarks (SWE-bench Verified, Terminal-Bench, GSO (code optimization), WebDev Arena), scored as percentile rank against every model released in the past year.
Coding score is a 0–100 percentile composite across that area’s benchmarks. Open a model for the raw scores.
Frequently asked questions
What is the best AI model for coding?
Claude Opus 4.7 (Anthropic) currently ranks first for coding on Model Beat, followed by Claude Opus 4.8 and Qwen 3.7 Max. Ranked by a 0–100 composite of coding benchmarks (SWE-bench Verified, Terminal-Bench, GSO (code optimization), WebDev Arena), scored as percentile rank against every model released in the past year.
Which is the most affordable strong coding model?
Among the top-ranked coding models, MiniMax-M3 is the cheapest at $0.30 per million input tokens.
How are these coding rankings calculated?
Ranked by a 0–100 composite of coding benchmarks (SWE-bench Verified, Terminal-Bench, GSO (code optimization), WebDev Arena), scored as percentile rank against every model released in the past year.
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.