Coding LLM Benchmark

โ† Back to leaderboard

Pricing & capacity

Avg cost
$1.20 per run
Input price
$1.75 / 1M tokens
Output price
$14.00 / 1M tokens
Context window
400K

Capabilities

Vision
Yes
Reasoning
Yes
Tool calls
Yes
Cursor
Yes
OpenRouter
Yes

Agent scores

Overall
56.3%
Issue Resolution
74.6%
Frontend
30.9%
Greenfield
37.5%
Testing
73.2%
Information Gathering
65.5%

Notes

Competitive issue resolution and testing. Weaker on frontend. Cost-effective for backend-heavy agentic workflows and automated bug fixing.