0

Claude Opus 4.7

Claude Opus 4.7 is an AI model from Anthropic.

Publisher
Anthropic
Family
Claude
Context
1M
Input
Output
License
proprietary
Released
16 Apr 2026

Cite

Notes

Only stored in your browser.

Attribution

Benchmark scores
frontiermathAALiveBenchmatharenaprime-hubOpenRewardVals AIEQ-BenchLech Mazur
Attribution policy →
Context
1M
Weights
Closed
API only
Input
$5
/1M tok
Output
$25
/1M tok
Blended
$10
#481/ 500/1M · 3:1
Speed
0
#106/ 499tok/s
Cache read
$0.50
0.10x input
Cache write
$6.25
1.25x input

Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter

Reasoning effortIndexSpeed
max40.70 t/s
Non-reasoning, high30.90 t/s

Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers

Reported on 35 evals across 15 domains - best 100.0% on Physgym Arena Medley Public · #1 of 6

Reported eval scores

35
Autonomous Skill Evolution3.2
Physgym Arena Medley Public100
Physgym Arena Drhard Public45.3
MMMLU91.5
SAGE56.1
MortgageTax70.3
TaxEval v275.3
CorpFin v266.1
Finance Agent (v2)51.5
LiveBench - Coding82.1
Terminal-Bench (Hard)51.5
LiveBench - Math93.1
LiveBench - Reasoning87.7
LiveBench - Data Analysis78.3
LiveBench - Language77.9
IFBench58.6
LiveBench - Instruction Following59.3
LiveBench79.7
Humanity's Last Exam (HLE)42.3
Vals Index56.1

Head-to-heads

29

benchmark comparisons against other models

vs GPT-5.532 shared evalsvs Gemini 3.1 Pro Preview31 shared evalsvs Claude Opus 4.830 shared evalsvs Claude Opus 4.629 shared evalsvs Claude Sonnet 4.629 shared evalsvs Claude Fable 528 shared evalsvs GPT-5.428 shared evalsvs Kimi K2.528 shared evalsvs GLM 5.128 shared evalsvs Qwen3.6 Plus27 shared evalsvs GPT-5.226 shared evalsvs GPT-5.4 Mini26 shared evalsvs GPT-5 Mini25 shared evalsvs Claude Sonnet 4.524 shared evalsvs Claude Opus 4.524 shared evalsvs Grok 4.1 Fast24 shared evalsvs DeepSeek V3.223 shared evalsvs GPT-5 Nano22 shared evalsvs Claude 4 Sonnet21 shared evalsvs GLM 4.721 shared evalsvs Gemini 2.5 Pro20 shared evalsvs gpt-oss-120b18 shared evalsvs GPT-517 shared evalsvs GPT-6 Astra14 shared evalsvs GPT-4o14 shared evalsvs GPT-4o-mini12 shared evalsvs GPT-4.1 Nano12 shared evalsvs GPT-4.1 Mini11 shared evalsvs GPT-4.111 shared evals