Coding LLM Benchmark

โ† Back to leaderboard

Pricing & capacity

Avg cost
$0.13 per run
Input price
$0.27 / 1M tokens
Output price
$1.10 / 1M tokens
Context window
128K

Capabilities

Vision
No
Reasoning
Yes
Tool calls
Yes
Cursor
Yes
OpenRouter
Yes

Agent scores

Overall
44.4%
Issue Resolution
71.6%
Frontend
27.9%
Greenfield
18.8%
Testing
53.6%
Information Gathering
50.3%

Notes

Open-source (MIT) reasoning model with very low cost. Good issue resolution, weaker testing. Ideal for self-hosted deployments needing cost-effective agentic coding.