Claude 3 Sonnet

deprecated by benchmark source

Anthropic · released 2024-03-04 · 0 offers

Context 200K tokens

Providers

No provider publishes an API price for this model yet, so no cost can be modeled.

2 of 7 inputs · 1 from the model family6 radar axes: DesignArena's two boards share one

2.5

Thin data · 2/7

AA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 2.4AA Agentic —Epoch ECI 120.8Software ECI —DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

4 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

1 of 4 values are Anthropic's own claims (†), not independent measurements; a matching independent result replaces a claim as soon as one exists.

Composite attachments (used in the score, not counted as exact benchmarks):

Humanity's Last Exam (AA text-only)73.6%2026-09-10
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.

GPQA Diamond (AA)1540.0%2026-09-10
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.

MMMUdeveloper's claim53.1%^{† self-reported by the developer}2026-09-10
MMMU published 2026-09-10 → · validation — A multimodal benchmark of 11.5K college-level questions across six disciplines and 30 subjects, with 30 heterogeneous image types.
CharXiv Reasoning val-v1.03632.2%2026-09-22
CharXiv Reasoning val-v1.0 → · validation — Can a multimodal model reason over the real, messy charts in scientific papers — combining values, trends and labels across a figure — rather than read off templated plots?

Missing coverage · 315 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.