Terminal-Bench 2.0activeCodingAgents
Terminal-Bench 2.0
Metric: % Tasks Completed (higher is better)Introduced: 2026
About
Second-generation terminal agent benchmark with 89 high-quality tasks spanning software engineering, machine learning, security, data science, and other real shell environments.
How to read this benchmark
This benchmark uses a scoring system where higher is better. Scores are useful for directional filtering and model shortlisting, not for universal quality ranking.
Interpretation checklist: prefer benchmarks that are closest to your workload style, then validate against the linked model pages for pricing, context window, and provider availability.
Trust when:
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- Model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Don't trust when:
- There is only one benchmark snapshot or the dataset appears stale.
- Benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Current modeled score band for tracked entries is roughly 69.3 – 59.1.
Window
Apr 20 to May 21
last 3 snapshots
Mean delta
-2.50
score points
Coverage
2
models in latest snapshot
Leaderboard preview (top 5)
- 1. Composer 2.569.3
- 2. DeepSeek V4 Pro67.9
- 3. Kimi K2.666.7
- 4. Claude Sonnet 4.659.1