BenchmarkTerminal-Bench Science
Terminal-Bench Science
A scientific task variant of Terminal-Bench, evaluating a model's capabilities in terminal operations related to scientific computing.
Timeline (last 90 days)
Oct 13
Vals AI uses benchmarks focused on real productized scenarios and agentic tasks, including long-chain benchmarks such as CUA-bench, Code Migration, Terminal-Bench Science, and SRE Bench.
Unverified50%
Sep 4
Claude 5.1 scored 52.6% on Terminal-Bench Science, more than doubling the previous generation's score of 24.7%.
Unverified60%
All Facts (2)
Unverified
Claude 5.1 scored 52.6% on Terminal-Bench Science, more than doubling the previous generation's score of 24.7%.
60%UnverifiedVals AI uses benchmarks focused on real productized scenarios and agentic tasks, including long-chain benchmarks such as CUA-bench, Code Migration, Terminal-Bench Science, and SRE Bench.
50%