Leaderboard 0 current results

Select models with +, then open Compare.

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Definition

Category: coding
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 46 min agomedium
Task: research-level scientific coding problems
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 46 min agomedium
Metric: accuracy · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 46 min agomedium
Paper: https://arxiv.org/abs/2407.13168
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 46 min agomedium
Website: scicode-bench.github.io
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 46 min agomedium

Each value shows its source, tier and observation time. Missing rows mean no source stated them. How results are recorded →

No relations recorded.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Paper

1 claims · 1 propertiesShow all properties

Paperpaper1

Claim history for Paper
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/abs/2407.13168	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New benchmarkBenchmarkSciCode
New benchmark: SciCode
registry
arxiv.org

Full timeline →

No documents recorded