ModelBeat
Models/Claude Opus 4.1
All models
A

Anthropic: Claude Opus 4.1

anthropic/claude-opus-4.1

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.

Context
200K
Input
$15 / 1M
Output
$75 / 1M
Released
Aug 5, 2025
Modalities
imagetextfiletext

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Claude Opus 4.1 lands among all models tracked on Model Beat.

28.0
Intelligence Index
Epoch AI
28th percentile of tracked models
34.0
Coding Index
Epoch AI
34th percentile of tracked models
31.0
Agentic Index
Epoch AI
31st percentile of tracked models

Reasoning

5 evals
GPQA Diamond77.3%

Graduate-level scientific reasoning

Humanity's Last Exam11.5%

Frontier of human expert knowledge

SimpleBench60.0%

Common-sense trick questions

SimpleQA Verified34.8%

Factual accuracy & hallucination

WeirdML42.8%

Novel ML problem-solving

Coding

2 evals
SWE-bench Verified73.3%

Real GitHub issue resolution

WebDev Arena1386

Human-rated web development

Math

3 evals
AIME 2024/202568.9%

Olympiad-qualifier math

FrontierMath7.2%

Research-level math problems

FrontierMath Tier 44.2%

Hardest research math

Agentic & Tools

3 evals
GDPval (win/tie rate)47.6%

Economically valuable work

METR task horizon1.9 h

Autonomous task length

Terminal-Bench38.0%

Command-line agentic tasks

Model & benchmark data from Epoch AI (CC BY); pricing, specs & descriptions from OpenRouter.