Terminal-Bench 2.0Agentic
61.7/ 100
Verified
Last Verified: 2026-03-19Cursor AI
Agent performance in realistic terminal workflows (v2.0 leaderboard).
Beta version: *Information might not be fully accurate. Please report any discrepancies.
Beta version: *Information might not be fully accurate. Please report any discrepancies.
Latest Data
2026-03-19
Context Window
256k
tokens
Input Cost
$0.50
per 1M tokens
Output Cost
$2.50
per 1M tokens
Parameters
Based on Kimi K2.5 (1T MoE)
model footprint
Performance Analysis // Verified Benchmarks
Agent performance in realistic terminal workflows (v2.0 leaderboard).
Software engineering performance across multilingual codebases.