← All models
Compare

Claude Opus 4.5 vs Grok 4.6

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

Claude Opus 4.5Grok 4.6
AttributeClaude Opus 4.5AnthropicGrok 4.6xAI · 3 in the news
Scores
Intelligence (ECI)150156
Coding6290
Math2891
Reasoning & Knowledge5573
Agentic & Tools5295
Specifications
DeveloperAnthropicxAI
FamilyClaudeGrok
ReleasedNov 24, 2025Aug 12, 2026
Parameters
AvailabilityAPI accessAPI access
Context window200K500K
Price — $/M input$5.00$2.00
Price — $/M output$25.00$6.00
Inputsfile, image, texttext, image, file
Outputstexttext
Benchmarks
AIME 2024/202586%99%
APEX21%65%
ARC-AGI80%88%
ARC-AGI-238%67%
FrontierMath21%
FrontierMath Tier 44%
GDPval (win/tie rate)60%
GPQA Diamond86%94%
GSO (code optimization)27%
Humanity's Last Exam25%43%
LiveCodeBench87%
METR task horizon4.9 h
MMLU-Pro90%
SciCode50%56%
SimpleBench62%76%
SimpleQA Verified46%49%
SWE-bench Verified77%
Terminal-Bench63%
WebDev Arena14941618
WeirdML64%67%
τ²-bench89%

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.