Rankings / Anthropic

Claude 3.5 Sonnet (October 2024)

release date unknown

BenchAtlas Index

as of 2026-07-14

Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

4 results

factuality

MASK

72.3 %

69.9–74.8

independent

Scale Labs

knowledge science

Humanity's Last Exam

contamination=This model was used as an initial filter for the dataset. · implementation=scale

4.1 %

3.3–4.9

independent

Scale Labs

multimodal

VISTA

38.7 %

38.2–39.2

independent

Scale Labs

reasoning math

EnigmaEval

0.9 %

0.4–1.5

independent

Scale Labs