Claude Code · AI Agent · Claude · GitHub · GPT · terminal-bench-science.ai
Terminal-Bench-Science: Evaluating AI agents on scientific research workflows
Compiled by KHAO Editorial — aggregated from 1 source + 2 references discovered via search. See llms.txt for citation guidance.
◌ Single Source
Terminal-Bench-Science evaluates AI agents on workflows from researchers' own work.
Key facts
- GPT-5.6 Sol matches Claude Fable 5's performance at less than a third of the cost ($4.2k vs $14.2k)
- Claude Opus 5 leads both GPT-5.6 Sol and Claude Fable 5 in every domain except the mathematical sciences, where Claude Fable 5 (33.3%) and GPT-5.6 Sol (31.4%) take the top two spots
- GPT-5.6 Sol and Claude Opus 5 reach the highest resolution rates at greater cost, with Opus 5 at $7.0k
- Claude Opus 5 with Claude Code achieves the highest resolution rate at 30.0%, followed by GPT-5.6 Sol with Codex at 22.4% and Claude Fable 5 with Claude Code at 21.4%
Summary
Terminal-Bench-Science is a benchmark led by researchers at Stanford University and built by the team behind Terminal-Bench in collaboration with domain experts from a range of scientific disciplines and research institutions around the world. Terminal-Bench-Science is a continuous benchmark that evolves alongside frontier AI, creating a feedback loop between scientific needs and AI development. While Terminal-Bench has driven progress in AI agents for software engineering, Terminal-Bench-Science brings the same ambition to science. Achieving this requires benchmarks that reflect real scientific practice, provide verifiable evidence of capability, and evolve alongside the AI frontier. The team need benchmarks drawn from real scientific workflows.