Atlas

Benchmarks

AstaBench (2026 scoring)

Ai2 scientific-agent suite covering literature, code execution, data analysis, and end-to-end discovery. Container for test-set components under the April 2026 scoring update; the overlapping suite and category composites are not imported. ScholarQA-CS2 and end-to-end discovery were rescored with replacement judges. Coverage includes thirteen identified ReAct baselines, with their source-linked harness versions preserved.

Models
0
Top score
—
Leader
—
Updated
—
Resolution
—
Saturation
—

No signal or difficulty estimate. Held out of the fit by design.

This is a benchmark-family page. Scores are recorded on the component benchmarks below rather than directly on the parent, because the components use different score scales and directions.

MetricModelsLeaderDirectionDate
ArxivDIGESTables-Clean (AstaBench 2026)13Opus 4.70.4higher is better—
CORE-Bench-Hard (AstaBench 2026)13GPT-5.40.9higher is better—
DiscoveryBench (AstaBench 2026)13GPT-5.50.4higher is better—
DS-1000 (AstaBench 2026)13Gemini 3.1 Pro Preview0.8higher is better—
E2E-Bench (AstaBench 2026)13Opus 4.70.7higher is better—
E2E-Bench-Hard (AstaBench 2026)13Opus 4.70.7higher is better—
LitQA2-FullText (AstaBench 2026)13Opus 4.60.9higher is better—
LitQA2-FullText-Search (AstaBench 2026)13Opus 4.60.9higher is better—
PaperFindingBench (AstaBench 2026)13Opus 4.70.4higher is better—
ScholarQA-CS2 (AstaBench 2026)13GPT-5.40.9higher is better—
SUPER-Expert (AstaBench 2026)13Opus 4.70.4higher is better—
Loading Atlas data…