SGI-Bench: Scientist-Aligned Benchmark for LLM Evaluation Across 10 Disciplines

SGI-Bench is a scientist-aligned benchmark for evaluating Scientific General Intelligence across the full inquiry cycle. It spans 10 disciplines and contains more than 1,000 expert-curated samples inspired by Science's 125 Big Questions. The dataset was created by InternScience and was last updated on 2026-06-02.

Use Cases

• Benchmarking LLM performance on scientific inquiry workflows based on the described Deliberation, Conception, Action, and Perception cycle.
• Evaluating model capabilities across 10 scientific disciplines using the more than 1,000 expert-curated samples.
• Developing agentic evaluation frameworks for scientific tasks as mentioned in the description.

Strengths

• More than 1,000 expert-curated samples provide a substantial test set.
• Benchmark spans 10 distinct scientific disciplines for broad coverage.
• Evaluation framework is designed around a scientist-aligned, agentic workflow.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Freshness should be verified as the last update timestamp is 2026-06-02.

Provenance

Source

InternScience via Hugging Face.

Collection Method

Expert-curated samples inspired by Science's 125 Big Questions.

Freshness

Last updated 2026-06-02 12:02:31.