Inference
EN
Anthropic

Claude Sonnet 4

Claude Sonnet 4 is a model from Anthropic. 15 benchmarks count toward its index, in 6 categories.

  • Input: image · text · file
  • Released 2025-05
RankedEnough results for an index.
IndexAll categories, out of 100.43.0±5.2Median 51.0
CoverageIndex weight that has results.90%
SpeedOutput tokens per second.49/sMedian 67/s
First tokenSeconds to the first output token.1.1 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$3.00Median $0.60
Output / 1MUS dollars per 1M output tokens.$15.00Median $2.55
ContextMaximum tokens in one request.200KMedian 262K
EloLMArena rating and rank.1339±4 #220Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
anthropic/claude-sonnet-4
Max outputMaximum output tokens per request.
64K
Knowledge cutoffLast date of training data.
31 Jan 2025
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
No
Cache read / 1MUS dollars per 1M cached tokens.
$0.30
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted49.4—
CodingCode writing and repair.3 counted46.2159 / 209
ReasoningLogic problems and puzzles.2 counted38.9170 / 227
MultimodalTasks with images and text.1 counted49.4—
KnowledgeFacts and expert knowledge.2 counted44.5170 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.6 counted38.9127 / 168

Results

15 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
SWE-bench Verified · SWE-bench/experimentsCoding74.8%6 / 65
MATH level 5Math84.4% ±1.023 / 88
τ²-bench RetailAgentic80.5%10 / 23
MATH 500Math90.3% ±1.326 / 59
GPQA diamond · Epoch AIKnowledge77.0% ±2.997 / 217
OTIS Mock AIME 2024-2025Math61.1% ±7.0111 / 200
τ²-bench AirlineAgentic60.0%13 / 22
IOI v1Coding6.5% ±2.141 / 61
MMMU ProMultimodal72.4% ±1.164 / 92
MMLU ProKnowledge79.4% ±0.495 / 135
GPQA Diamond · Vals AIKnowledge69.4% ±2.395 / 135
FrontierMath-2025-02-28-PrivateMath4.1% ±1.249 / 69
AIMEMath38.5% ±1.071 / 95
LiveCodeBenchCoding59.7% ±1.2107 / 142
ARC-AGI-2 (semi-private)Reasoning1.3%103 / 131
ARC-AGI-1 (semi-private)Reasoning23.8%101 / 126
FrontierMath-Tier-4-2025-07-01-PrivateMath0.0%45 / 55
FrontierMath-Tier-4-2025-07-01-PublicMath0.0%3 / 36
MGSMMultilingual93.0% ±1.611 / 74
SWE-bench Multimodal · swebench.comMultimodal34.4%2 / 8
LegalBenchLegal83.0% ±0.462 / 149
MedQAHealthcare90.3% ±0.346 / 95
FrontierMath-2025-02-28-PublicMath0.0%33 / 64
MortgageTaxFinance62.5% ±1.054 / 97
TaxEval v2Finance69.6% ±0.997 / 143
CorpFin v2Finance54.7% ±1.092 / 131
ARC-AGI-2 (public eval)Reasoning2.1%86 / 122
MedCodeHealthcare33.9% ±1.982 / 106
MedScribeHealthcare72.4% ±1.988 / 109
ARC-AGI-1 (public eval)Reasoning33.0%96 / 116

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedEpoch AICC BYSierra ResearchMITSWE-bench teamNo licence statedARC Prize FoundationTerms restrict reuse

History

5 releases
Index44.1 → 43.0
23 Oct 202612 Nov 2026
Output / 1M$15.00 → $15.00
23 Oct 202612 Nov 2026

Questions

How much does Claude Sonnet 4 cost?
$3.00 per 1M input tokens, $15.00 per 1M output tokens.
How good is Claude Sonnet 4?
Its index is 43.0 out of 100. That is place 193 of 283 ranked models.
What is Claude Sonnet 4 best at?
Knowledge: 44.5 out of 100, place 170 of 268.
How fast is Claude Sonnet 4?
49 output tokens per second, 1.1 s to the first token.
What is the context window of Claude Sonnet 4?
200K tokens.
When was Claude Sonnet 4 released?
May 2025.

Badge

Claude Sonnet 4 on Inference360: place 193 of 283, index 43.0
HTML
<a href="https://inference360.ai/models/anthropic-claude-sonnet-4"><img src="https://inference360.ai/badges/anthropic-claude-sonnet-4.svg" alt="Claude Sonnet 4 on Inference360: place 193 of 283, index 43.0" height="20"></a>
Markdown
[![Claude Sonnet 4 on Inference360: place 193 of 283, index 43.0](https://inference360.ai/badges/anthropic-claude-sonnet-4.svg)](https://inference360.ai/models/anthropic-claude-sonnet-4)

Compare with

Claude Haiku 4.543.2Kimi K2 Instruct43.2Mistral Medium 3.542.7

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Anthropic

All models
Claude 4 Opus Thinking47.0Claude 4 Sonnet39.5Claude 4 OpusUnrankedClaude 4.1 Opus Thinking47.0Claude 4.1 OpusUnranked