Terminal-Bench-Science
1 article tagged with Terminal-Bench-Science
September 2, 2026
model releaseAnthropic
Anthropic Releases Claude Fable 5.1, Claims 52.6% on New Terminal-Bench-Science Benchmark
Anthropic released Claude Fable (and Mythos) 5.1, claiming a 52.6% score on the new Terminal-Bench-Science 0.1 benchmark — up sharply from 24.7% for Fable 5. Independent testing shows the model's five reasoning levels produce dramatically different output token counts and costs for identical prompts, ranging from $0.10 to $3.30 per request.