Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Task (Agentic Coding) on IFBench
Loading...
77.1
Score
Gemini 3.1 Pro
52.14
58.62
65.1
71.58
Mar 29, 2026
Score
Updated 19d ago
Evaluation Results
Method
Method
Links
Score
Gemini 3.1 Pro
Source=artificialanaly...
2026.03
77.1
MiniMax M2.7
Source=artificialanaly...
2026.03
75.7
GPT-5.4
Source=artificialanaly...
2026.03
73.9
GLM-5
Source=artificialanaly...
2026.03
72.3
KAT-Coder-V2
Evaluation Environment...
2026.03
67
Claude Opus 4.6
Source=artificialanaly...
2026.03
53.1
Feedback
Search any
task
Search any
task