Inference
EN
Anthropic

Claude Opus 4.7

Claude Opus 4.7 is a standard model from Anthropic. 43 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Standard
  • Input: text · image · file
  • Released 2026-04
RankedEnough results for an index.
IndexAll categories, out of 100.62.0±3.0Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.47/sMedian 67/s
First tokenSeconds to the first output token.1.0 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$5.00batch $2.50Median $0.60
Output / 1MUS dollars per 1M output tokens.$25.00batch $12.50 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.1483±4 #18Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
anthropic/claude-opus-4.7
Max outputMaximum output tokens per request.
128K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.50
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
9 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
GMI CloudHost$4.50$22.50410K
Amazon BedrockCloud$5.00$25.001M
DatabricksCloud$5.00$25.001M
DigitalOceanCloud$5.00$25.00200K
Google Vertex AICloud$5.00$25.001M
Microsoft AzureCloud$5.00$25.001M
OpenRouterRouter$5.00$25.001M
SAP AI CoreCloud$5.00$25.001M
Snowflake CortexCloud$5.00$25.001M

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.8 counted60.663 / 218
CodingCode writing and repair.10 counted64.546 / 209
ReasoningLogic problems and puzzles.8 counted61.161 / 227
MultimodalTasks with images and text.2 counted61.339 / 84
KnowledgeFacts and expert knowledge.6 counted61.856 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.2 counted45.737 / 63
MathMath problems.7 counted64.334 / 168

Results

43 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
SWE-Bench verified · Epoch AICoding83.5% ±1.71 / 32
Terminal-Bench 2.0 · Vals AIAgentic68.5% ±5.03 / 66
Gert Labs Composite Game BenchmarkAgentic65.6%3 / 52
MMLU ProKnowledge89.9% ±0.38 / 135
AIMEMath96.3% ±0.57 / 95
FrontierMath-2025-02-28-PrivateMath43.8% ±2.96 / 69
LiveBench CodingCoding82.1%9 / 66
FrontierMath-Tier-4-2025-07-01-PrivateMath22.9% ±6.18 / 55
IOI v1Coding47.1% ±8.710 / 61
GPQA Diamond · Vals AIKnowledge90.2% ±1.525 / 135
Artificial Analysis Omniscience AccuracyKnowledge44.7%39 / 164
SWE-benchCoding82.0% ±1.721 / 87
LiveCodeBenchCoding85.1% ±1.035 / 142
Artificial Analysis GPQA DiamondKnowledge88.5%50 / 199
MMMU ProMultimodal85.5% ±0.824 / 92
Terminal-Bench HardAgentic54.5%6 / 23
τ²-bench BankingAgentic40.2%8 / 28
GPQA diamond · Epoch AIKnowledge86.4% ±2.466 / 217
SimpleQA VerifiedKnowledge51.7% ±1.628 / 91
LiveBench Data AnalysisReasoning78.3%25 / 80
Artificial Analysis Humanity's Last ExamKnowledge33.3%70 / 222
FrontierMath-Tiers-1-3-v2-PrivateMath70.2% ±2.729 / 90
Code MigrationCoding43.9% ±4.225 / 77
LiveBench MathematicsMath92.9%22 / 66
OTIS Mock AIME 2024-2025Math86.7% ±5.169 / 200
LiveBench ReasoningReasoning87.2%29 / 80
React Native EvalsCoding82.8%6 / 16
Chess PuzzlesReasoning41.0% ±4.934 / 90
Vibe Code Bench v1.1Coding71.0% ±4.547 / 123
Critical Physics TasksReasoning5.1%83 / 214
Artificial Analysis MMMU-ProMultimodal76.4%44 / 113
Terminal-Bench 2.1 · Vals AIAgentic68.5% ±1.331 / 75
Artificial Analysis Long Context ReasoningReasoning75.7%92 / 217
Mystery Game PuzzlesReasoning28.0% ±4.534 / 80
FrontierMath-Tier-4-v2-PrivateMath31.7% ±7.432 / 72
τ²-Bench Tool-Agent-User EvaluationAgentic74.0%78 / 149
LiveBench Instruction FollowingInstruction66.7%37 / 66
ParseBench: document parsing for AI agents (LlamaIndex leaderboard)Multimodal63.3%23 / 39
LiveBench LanguageKnowledge77.9%39 / 66
LiveBench Agentic CodingAgentic50.7%40 / 66
Artificial Analysis IFBenchInstruction43.6%91 / 146
EBR-benchReasoning19.0%20 / 31
Furniture AssemblyReasoning33.3% ±6.126 / 37
PostTrainBench v1.1Coding28.6%11 / 15
MirrorCodeCoding31.1% ±9.030 / 39
OSWorld 2.0Agentic13.9%20 / 25
ARC-AGI-3 (semi-private)Reasoning0.2%21 / 26
FrontierCode 1.1 MainCoding38.5%14 / 17
ApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable jobAgentic7.0%15 / 18
Finance Agent v1.1Finance64.4% ±2.81 / 51
MortgageTaxFinance70.3% ±0.93 / 97
FrontierMath-2025-02-28-PublicMath90.0% ±10.02 / 64
MedCodeHealthcare54.9% ±2.27 / 106
FrontierMath-Tier-4-2025-07-01-PublicMath0.0%3 / 36
CaseLaw v2Legal68.4% ±0.45 / 53
TaxEval v2Finance75.3% ±0.819 / 143
LegalBenchLegal85.3% ±0.522 / 149
CorpFin v2Finance66.1% ±0.921 / 131
EMBFinance63.7% ±3.127 / 75
Legal Research BenchLegal38.5% ±3.439 / 90
MedScribeHealthcare83.0% ±2.048 / 109
Finance Agent (v2)Finance51.5% ±0.540 / 79
ProgramBenchCoding0.0%34 / 65
Tax Agent BenchFinance23.7% ±3.147 / 82
ResearchClawBenchAgentic20.7%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedLiveBenchNo licence statedEpoch AICC BYSierra ResearchMITARC Prize FoundationTerms restrict reusemodels.devMIT

History

5 releases
Index63.1 → 62.0
23 Oct 202612 Nov 2026
Output / 1M$25.00 → $25.00
23 Oct 202612 Nov 2026

Questions

How much does Claude Opus 4.7 cost?
$5.00 per 1M input tokens, $25.00 per 1M output tokens.
How good is Claude Opus 4.7?
Its index is 62.0 out of 100. That is place 63 of 283 ranked models.
What is Claude Opus 4.7 best at?
Math: 64.3 out of 100, place 34 of 168.
How fast is Claude Opus 4.7?
47 output tokens per second, 1.0 s to the first token.
What is the context window of Claude Opus 4.7?
1M tokens.
Is Claude Opus 4.7 open source?
No. Its weights are not published.
When was Claude Opus 4.7 released?
April 2026.

Badge

Claude Opus 4.7 on Inference360: place 63 of 283, index 62.0
HTML
<a href="https://inference360.ai/models/claude-opus-4-7"><img src="https://inference360.ai/badges/claude-opus-4-7.svg" alt="Claude Opus 4.7 on Inference360: place 63 of 283, index 62.0" height="20"></a>
Markdown
[![Claude Opus 4.7 on Inference360: place 63 of 283, index 62.0](https://inference360.ai/badges/claude-opus-4-7.svg)](https://inference360.ai/models/claude-opus-4-7)

Compare with

GPT-5.3 Codex62.0DeepSeek V4 Flash 073161.9Gemini 3.1 Pro62.3Claude Opus 4.7 (Adaptive)63.2Claude Opus 4.867.7

Lower price

dots3-note Preview63.4 · FreeGLM-5.3-Flash63.1 · $0.078/1MLing 3.1 Flash67.2 · $0.135/1M

More from Anthropic

All models
Claude Opus 4.7 (Adaptive)63.2Claude Opus LatestUnrankedClaude Mythos PreviewUnrankedClaude Sonnet LatestUnrankedClaude Haiku LatestUnranked