Anthropic · proprietary

Claude Sonnet 4

Claude Sonnet 4 by Anthropic appears in 1 source with Reasoning at 30.27. Best read for Code quality, LLM, Multimodal.

CreatorAnthropic

Release date2025-05-22

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank57ranking · source_rank

Reasoning30.27reasoning · index_reasoning

Math21.77math · index_math

Coding21.11coding · index_code

Writing25.3writing · index_communication

Vision16.46multimodal · index_vision

Tool calling23.36tool_calling · index_tool_calling

Healthcare25.55domain · index_healthcare

GPQA75.4 %reasoning · gpqa_score

AIME 202570.5 %math · aime_2025_score

SWE-bench Verified72.7 %coding · swe_bench_verified_score

Code Arena881.62 %coding · coding_arena_score

MMMLU86.5 %reasoning · mmmlu_score

MMMU74.4 %multimodal · mmmu_score

Terminal Bench35.5 %coding · terminal_bench_score

TAU2 Retail80.5 %agent · tau_bench_retail_score

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Claude Sonnet 4 verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.