Search the entire AI Orbit.

PostTrainBench Lite — official/provider-reported evaluation result. Methodology conditions are preserved in the...

Independent live speech-to-text benchmark on pinned, versioned datasets under production-realistic conditions. W...

MMMU — official/provider-reported evaluation result. Methodology conditions are preserved in the result notes.

MMLU — official/provider-reported evaluation result. Methodology conditions are preserved in the result notes.

AIME 2025 — official/provider-reported evaluation result. Methodology conditions are preserved in the result not...

FrontierMath (Python tool only) — official/provider-reported evaluation result. Methodology conditions are prese...

Humanity's Last Exam (No Tools) — official/provider-reported evaluation result. Methodology conditions are prese...

HMMT 2025 — official/provider-reported evaluation result. Methodology conditions are preserved in the result not...

MMMU-Pro (Average Standard + Vision) — official/provider-reported evaluation result. Methodology conditions are...

CharXiv Reasoning (Python Enabled) — official/provider-reported evaluation result. Methodology conditions are pr...

VideoMMMU (Max 256 Frames) — official/provider-reported evaluation result. Methodology conditions are preserved...

ERQA — official/provider-reported evaluation result. Methodology conditions are preserved in the result notes.

SWE-bench Verified (OpenAI 477 Tasks) — official/provider-reported evaluation result. Methodology conditions are...

Aider Polyglot (Diff) — official/provider-reported evaluation result. Methodology conditions are preserved in th...

Agents' Last Exam — official/provider-reported evaluation result. Methodology conditions are preserved in the re...

Big Finance Bench — official/provider-reported evaluation result. Methodology conditions are preserved in the re...

SWE-Bench Pro — official/provider-reported evaluation result. Methodology conditions are preserved in the result...

Terminal-Bench 2.1 — official/provider-reported evaluation result. Methodology conditions are preserved in the r...

GeneBench Pro — official/provider-reported evaluation result. Methodology conditions are preserved in the result...

LifeSciBench — official/provider-reported evaluation result. Methodology conditions are preserved in the result...

HealthBench Professional — official/provider-reported evaluation result. Methodology conditions are preserved in...

OSWorld 2.0 — official/provider-reported evaluation result. Methodology conditions are preserved in the result n...

BrowseComp — official/provider-reported evaluation result. Methodology conditions are preserved in the result no...

Capture-the-Flag Challenges — official/provider-reported evaluation result. Methodology conditions are preserved...

ExploitGym — official/provider-reported evaluation result. Methodology conditions are preserved in the result no...

Internal Research Debugging Evaluation — official/provider-reported evaluation result. Methodology conditions ar...

KernelGen 1P — official/provider-reported evaluation result. Methodology conditions are preserved in the result...

MMMU Pro (No Tools) — official/provider-reported evaluation result. Methodology conditions are preserved in the...

MMMU Pro (With Tools) — official/provider-reported evaluation result. Methodology conditions are preserved in th...

FrontierMath Tier 1-3 v2 — official/provider-reported evaluation result. Methodology conditions are preserved in...