Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Terminal-based task execution on Terminal-Bench 2.0
Loading...
65.2
Resolved %
SageAgent
51.368
54.959
58.55
62.141
Feb 18, 2026
Resolved %
Updated 4d ago
Evaluation Results
Method
Method
Links
Resolved %
SageAgent
Model=Gemini 3 Pro, AD...
2026.02
65.2
Ante
Model=Gemini 3 Pro
2026.02
64.7
Codex CLI
Model=GPT-5.2 (xhigh),...
2026.02
62.9
Claude Code
Model=Claude Opus 4.5,...
2026.02
52.1
OpenHands
Model=Claude Opus 4.5,...
2026.02
51.9
Feedback
Search any
task
Search any
task