Claude Sonnet 4.5

anthropic/claude-4.5-sonnet-20250929

This model accepts text, image, and file inputs and returns text outputs. It has a context length of 1,000,000 tokens and supports tools and reasoning. Pricing is $3 per million input tokens and $15 per million output tokens.

  • tool use
  • structured outputs
  • reasoning

At a glance

provideranthropic
releasedSep 26, 2025
context1M
input / M$3

Specifications

What the API gives you

Context window
1M tokens
Max output
64K tokens
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Cache read
$0.30 / 1M tokens
Modalities
text, image, file → text
Knowledge cutoff
Jan 31, 2025
Released
Sep 26, 2025

Measured evidence

Public benchmark record

BFCL
73.2%2026-10-21
Design Arena Coding
1183 Elo2026-10-21
Design Arena Full-stack Agent
1050 Elo2026-10-14
Design Arena UI
1161 Elo2026-10-21
Design Arena Web-app Agent
1060 Elo2026-10-21
Design Arena Website
1190 Elo2026-10-21
FACTS Grounding
58.7%2025-10-01evaluated 2025-10-01
FrontierMath Tiers 1-3 (Epoch AI)
23.9% ± 2.52026-06-11evaluated 2026-06-11
GPQA Diamond (Epoch AI)
78.8% ± 2.92025-10-28evaluated 2025-10-28
GPQA Diamond (Epoch AI)
81.7% ± 2.82025-10-21evaluated 2025-10-21
GPQA Diamond (Epoch AI)
73.7% ± 3.12025-09-29evaluated 2025-09-29
LMArena Creative Writing
1425 Elo2026-10-20
LMArena Instruction Following
1458 Elo2026-10-20
LMArena Long Query
1475 Elo2026-10-20
LMArena Math
1449 Elo2026-10-20
LMArena Text
1456 Elo2026-10-20
LMArena Text Factuality
1446 Elo2026-10-20
LMArena WebDev
1394 Elo2026-10-19
OTIS Mock AIME (Epoch AI)
71.1% ± 6.82025-10-28evaluated 2025-10-28
OTIS Mock AIME (Epoch AI)
77.8% ± 6.32025-10-21evaluated 2025-10-21
OTIS Mock AIME (Epoch AI)
35.6% ± 7.22025-09-29evaluated 2025-09-29
SimpleQA Verified (Epoch AI)
30.7% ± 1.52026-08-27evaluated 2026-08-27
SimpleQA Verified (Epoch AI)
23.7% ± 1.32026-08-10evaluated 2026-08-10
SWE-bench Verified (verified-500)‡
71.4%2026-10-21mini-SWE-agent 2.0.0, high effort, evaluated 2026-02-17
tau2-bench (1.0.1)‡
25.3%2026-02-24enabled effort, evaluated 2026-02-24

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Frontend & UIEstablished evidence

    82% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Document SummarizationEstablished evidence

    65% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationEstablished evidence

    65% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGEstablished evidence

    62% of intended weighted task evidence across 3 independent sources. 5 of 7 configured evaluation feeds currently have results.

  • Best LLM for RAG & Long ContextEstablished evidence

    61% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for a General AssistantEstablished evidence

    59% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

Show all 42 tasks
  • Best LLM for Competition MathEstablished evidence

    56% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingEstablished evidence

    55% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    52% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Tool & Function CallingEstablished evidence

    46% of intended weighted task evidence across 2 independent sources. 6 of 7 configured evaluation feeds currently have results.

  • Best LLM for CodingEstablished evidence

    42% of intended weighted task evidence across 3 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for JSON & Schema OutputEstablished evidence

    29% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Structured Data ExtractionEstablished evidence

    29% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Debugging & Code ReviewEstablished evidence

    28% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsEstablished evidence

    27% of intended weighted task evidence across 2 independent sources. 9 of 9 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Roleplay & CharacterProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    56% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    56% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 3 of 3 configured evaluation feeds currently have results.

  • Best Open-Weight LLM for Self-HostingProvisional evidence

    27% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or LMArena Vision OCR. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or LMArena Vision OCR. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Vision & DocumentsProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or LMArena Vision Diagrams. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or LMArena Vision Diagrams. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Literary TranslationProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Everyday TranslationProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Computer & Browser UseProvisional evidence

    11% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 3 of 3 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    10% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    10% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.