Anthropic · proprietary

Claude Opus 4.5

Claude Opus 4.5 by Anthropic appears in 2 sources with Reasoning at 54.19. Best read for Code quality, Coding, LLM.

CreatorAnthropic

Release date2025-11-24

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank9ranking · source_rank

Reasoning54.19reasoning · index_reasoning

Math43.46math · index_math

Coding39.76coding · index_code

Writing35.61writing · index_communication

Vision29.2multimodal · index_vision

Tool calling29.67tool_calling · index_tool_calling

Healthcare24.38domain · index_healthcare

GPQA87 %reasoning · gpqa_score

SWE-bench Verified80.9 %coding · swe_bench_verified_score

Code Arena1,613.89 %coding · coding_arena_score

ARC-AGI v237.6 %reasoning · arc_agi_v2_score

MMMLU90.8 %reasoning · mmmlu_score

OSWorld66.3 %agent · osworld_score

MCP Atlas62.3 %tool_calling · mcp_atlas_score

Speed22.77 c/sperformance · throughput

Latency792.75 msperformance · latency

SWE-Bench Verified80.9 %metric

Evidence

Citations and source overlap

VellumTop models per benchmark from page-level structured data (JSON-LD).Retrieved 2026-05-20 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 Opus 4.5 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.