A benchmark for agentic software engineering tasks executed in real terminal environments. DeepSeek reports it in the agentic section, while BenchLM also mirrors it in coding for models that publish it as a developer-task signal.
BenchLM mirrors the published score view for Terminal-Bench 2.0. Claude Mythos 5 leads the public snapshot at 88.0% , followed by Claude Fable 5 (84.3%) and GPT-5.5 (82.0%). BenchLM does not use these results to rank models overall.
Claude Mythos 5
Anthropic
Claude Fable 5
Anthropic
GPT-5.5
OpenAI
The published Terminal-Bench 2.0 snapshot is tightly clustered at the top: Claude Mythos 5 sits at 88.0%, while the third row is only 6.0 points behind. The broader top-10 spread is 19.6 points, so the benchmark still separates strong models even when the leaders cluster.
29 models have been evaluated on Terminal-Bench 2.0. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. Terminal-Bench 2.0 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Terminal-based software tasks
Format
Interactive CLI agent evaluation
Difficulty
Professional software engineering
Terminal-Bench 2.0 focuses on realistic CLI and repository workflows rather than toy code generation. BenchLM keeps coding-category copies display-only unless the scoring weights include them.
Version
Terminal-Bench 2
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A benchmark for agentic software engineering tasks executed in real terminal environments. DeepSeek reports it in the agentic section, while BenchLM also mirrors it in coding for models that publish it as a developer-task signal.
Claude Mythos 5 by Anthropic currently leads with a score of 88.0% on Terminal-Bench 2.0.
29 AI models have been evaluated on Terminal-Bench 2.0 on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.