← All models
Compare

Claude Opus 4.1 vs Grok 4.5

Add, remove, or swap models to compare them side by side.

claude-opus-4-1Grok 4.5
AttributeClaude Opus 4.1AnthropicGrok 4.5xAI · 2 in the news
Scores
Intelligence (ECI)144154
Coding3089
Math1784
Reasoning & Knowledge2969
Agentic & Tools2074
Specifications
DeveloperAnthropicxAI
FamilyClaudeGrok
ReleasedAug 5, 2025Jul 8, 2026
Parameters
AvailabilityAPI accessAPI access
Context window200K500K
Price — $/M input$15.00$2.00
Price — $/M output$75.00$6.00
Inputsimage, text, filetext, image, file
Outputstexttext
Benchmarks
AIME 2024/202569%98%
FrontierMath7%
FrontierMath Tier 44%
GDPval (win/tie rate)48%
GPQA Diamond77%93%
Humanity's Last Exam12%40%
METR task horizon1.9 h
SimpleBench60%70%
SimpleQA Verified35%54%
SWE-bench Verified73%
Terminal-Bench38%
WebDev Arena13861551
WeirdML43%46%
APEX34%
ARC-AGI87%
ARC-AGI-253%
SciCode54%

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.