SGI-DeepResearch Gold: A Scientist-Aligned Benchmark for LLM Evaluation

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

Use Cases

• Benchmarking LLM performance on scientific deliberation tasks based on the described inquiry cycle
• Evaluating model conception abilities across 10 scientific disciplines
• Testing agentic action planning within a scientist-aligned framework
• Assessing perception and interpretation of complex scientific questions

Strengths

• More than 1,000 expert-curated samples provide a substantial evaluation corpus
• Benchmark spans 10 distinct scientific disciplines for broad coverage
• Evaluation framework is structured around the four-stage inquiry cycle: Deliberation, Conception, Action, and Perception

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Description metadata is limited; actual data quality requires manual inspection after download

Provenance

Source

InternScience

Collection Method

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

Freshness

Last updated 2026-06-02 12:04:08; freshness should be verified