Scientific and ML agents / Benchmark leaderboard
Terminal-Bench-Science
Computational research workflows across scientific fields; Harbor snapshot has 70 tasks.
No published company result yet.
This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.
Arrange an evaluation for your company →What this benchmark measures
Metrics
Per-task executable scientific verifiers.
Execution requirements
Harbor terminal/scientific agent with task-specific resources.
Scope and limitations
Resource-heavy tasks and continuously versioned releases; assess reproducibility and licenses per task.
Evaluation availability
Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.
Sources and company fit
- Original benchmark ↗Newer specialist
- Harbor · terminal-bench-science/terminal-bench-science ↗70 source tasks · Public · Public detail metadata + family research
Companies whose products may fit
Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.
Compatibility notes for each company
Anthropic: Capability-aligned; adapter/access to qualify
FutureHouse: Capability-aligned; adapter/access to qualify
Google DeepMind: Capability-aligned; adapter/access to qualify
NVIDIA: Research / simulator adaptation
OpenAI: Capability-aligned; adapter/access to qualify
Sakana AI: Capability-aligned; adapter/access to qualify