Live Benchmarks

Amika Benchmark

Performance results of AI coding models on Amika tasks, measuring success rate and execution time with high precision.

View on GitHubTotal tasks: 13Last run: 6/16/2026

Model Performance

ModelPassedAvg DurationSuccess Rate
#1
glm-4.7NEW
4481.1s
31%
#2
gemini-3-flash
3529.8s
23%
#3
gemini-3.1-pro
3563.8s
23%
#4
claude-4-6-sonnet
3591.1s
23%