Inference
EN
Anthropic

Claude Opus 4.7 (Adaptive)

Claude Opus 4.7 (Adaptive) is a reasoning model from Anthropic in the Claude Opus 4.7 family. 24 benchmarks count toward its index, in 6 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2026-04
RankedEnough results for an index.
IndexAll categories, out of 100.63.2±4.8Median 51.0
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.$5.00Median $0.60
Output / 1MUS dollars per 1M output tokens.$25.00Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.12 counted63.552 / 218
CodingCode writing and repair.2 counted64.744 / 209
ReasoningLogic problems and puzzles.2 counted60.763 / 227
MultimodalTasks with images and text.4 counted60.440 / 84
KnowledgeFacts and expert knowledge.3 counted69.123 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted43.8—
MathMath problems.None counted——

Results

24 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Graduate-Level Google-Proof Q&AKnowledge94.2%5 / 141
Software Engineering Benchmark VerifiedCoding87.6%6 / 114
GPQA Diamond · BenchLMKnowledge94.2%6 / 84
CharXiv ReasoningMultimodal91.0%6 / 49
Artificial Analysis GPQA DiamondKnowledge91.4%26 / 199
Artificial Analysis Omniscience AccuracyKnowledge48.9%23 / 164
Terminal-Bench 2.0 · BenchLMAgentic69.4%6 / 41
Artificial Analysis Humanity's Last ExamKnowledge42.3%39 / 222
Humanity's Last ExamKnowledge54.7%15 / 77
Humanity's Last Exam without toolsKnowledge46.9%12 / 53
SWE-bench ProCoding64.3%19 / 83
Critical Physics TasksReasoning12.0%57 / 214
Artificial Analysis Long Context ReasoningReasoning78.7%61 / 217
Artificial Analysis MMMU-ProMultimodal78.8%32 / 113
τ²-Bench Tool-Agent-User EvaluationAgentic88.6%46 / 149
GDPval-AA normalizedAgentic42.6%43 / 133
MCP AtlasAgentic77.3%18 / 52
OSWorld-VerifiedAgentic78.0%15 / 37
Artificial Analysis IFBenchInstruction58.6%64 / 146
Artificial Analysis ITBench-AAAgentic46.7%11 / 24
JobBenchAgentic45.9%17 / 36
BrowseCompAgentic79.3%30 / 63
CharXiv Reasoning without toolsMultimodal82.1%12 / 17
Artificial Analysis Terminal-Bench v2.1Agentic83.1%15 / 21
OSWorld 2.0Agentic18.2%18 / 25
Artificial Analysis AnalystAgentAgentic43.8%19 / 26
CyberGymAgentic73.1%22 / 29
OfficeQA ProMultimodal43.6%16 / 16
OpenAI MRCR v2 8-needle 128K-256KReasoning59.2%—

Sources

BenchLMCC BY-NC 4.0

History

5 releases
Index63.8 → 63.2
23 Oct 202612 Nov 2026
Output / 1M$25.00 → $25.00
23 Oct 202612 Nov 2026

Questions

How much does Claude Opus 4.7 (Adaptive) cost?
$5.00 per 1M input tokens, $25.00 per 1M output tokens.
How good is Claude Opus 4.7 (Adaptive)?
Its index is 63.2 out of 100. That is place 59 of 283 ranked models.
What is Claude Opus 4.7 (Adaptive) best at?
Knowledge: 69.1 out of 100, place 23 of 268.
What is the context window of Claude Opus 4.7 (Adaptive)?
1M tokens.
Is Claude Opus 4.7 (Adaptive) open source?
No. Its weights are not published.
When was Claude Opus 4.7 (Adaptive) released?
April 2026.

Badge

Claude Opus 4.7 (Adaptive) on Inference360: place 59 of 283, index 63.2
HTML
<a href="https://inference360.ai/models/claude-opus-4-7-adaptive"><img src="https://inference360.ai/badges/claude-opus-4-7-adaptive.svg" alt="Claude Opus 4.7 (Adaptive) on Inference360: place 59 of 283, index 63.2" height="20"></a>
Markdown
[![Claude Opus 4.7 (Adaptive) on Inference360: place 59 of 283, index 63.2](https://inference360.ai/badges/claude-opus-4-7-adaptive.svg)](https://inference360.ai/models/claude-opus-4-7-adaptive)

Compare with

dots3-note Preview63.4GLM-5.3-Flash63.1Qwen3.8-Omni-Flash62.7Claude Opus 4.762.0Claude Sonnet 4.657.0

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 4.762.0Claude Opus LatestUnrankedClaude Mythos PreviewUnrankedClaude Sonnet LatestUnrankedClaude Haiku LatestUnranked