MMODELYST
Models/Claude Opus 4.5
MDL

Claude Opus 4.5

Anthropic

Verified against Artificial Analysis · Jul 13, 2026
Capability
92
percentile index
Price /M
$5 / $25
in / out
Context
200K
tokens
Avg score
70.1
10 benchmarks
AA Intelligence
40.8
index
Speed
57 tok/s
TTFT 11s
Released
Nov 24, 2025
About

Claude Opus 4.5 is a proprietary model in the Claude family from Anthropic. Benchmarked on 10 evals, averaging 70.1.

Benchmark scores · 10
avg 70.1 — higher is better
AIME
91.3
MMLU-Pro
89.5
τ²-bench
89.5
LiveCodeBench
87.1
GPQA Diamond
86.6
AA Long-Context Reasoning
74
IFBench
58
SciCode
49.5
Terminal-Bench Hard
47
Humanity's Last Exam
28.4
Details
PublisherAnthropic
FamilyClaude
Parameters
License
WeightsClosed
ReleasedNov 24, 2025
Performance & price
Output speed57 tok/s
Latency (TTFT)11s
Price in / out$5 / $25 per 1M
Blended price$10 / 1M
Math index91.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$25/M