Coding LLM Benchmark

โ† Back to leaderboard

Pricing & capacity

Avg cost
$1.77 per run
Input price
$5.00 / 1M tokens
Output price
$25.00 / 1M tokens
Context window
200K

Capabilities

Vision
Yes
Reasoning
Yes
Tool calls
Yes
Cursor
Yes
OpenRouter
Yes

Agent scores

Overall
60.6%
Issue Resolution
76.6%
Frontend
41.2%
Greenfield
37.5%
Testing
78.5%
Information Gathering
69.1%

Notes

Top-tier issue resolution and testing. Best suited for teams using extended thinking on complex debugging workflows.