The Model Index
Up to four models

Grok 4.1 Fast vs Claude Sonnet 4.5

On the index (GPT-4 = 100), Grok 4.1 Fast scores 144 and Claude Sonnet 4.5 144. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Grok 4.1 Fast
Presets
Grok 4.1 Fast
144126–163
WeightsClosed
ReleasedNov 2025
Price in / out–
Context–
Core tests taken0 of 9
Claude Sonnet 4.5
144129–160
WeightsClosed
ReleasedSep 2025
Price in / out$3.0 / $15
Context1M
Core tests taken6 of 9

Grok 4.1 Fast and Claude Sonnet 4.5 are too close to call (0 points apart, within the uncertainty).

Test by testthird-party results

Grok 4.1 FastClaude Sonnet 4.5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProSimpleBenchSimpleBenchMATHSMGSMMGSMCODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSDTBenchDTBenchPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTaxEval v2TaxEval v2
Every result as a table
TestGrok 4.1 FastClaude Sonnet 4.5
Reasoning & knowledge
GPQA Diamond (Vals AI)84.3%81.6%
MMLU Pro84.2%87.4%
MMMU Pro72.7%79.3%
SimpleBench56.0%54.3%
Maths
MGSM89.5%94.3%
Coding
LiveCodeBench80.6%73.0%
SWE-bench41.4%70.0%
Vibe Code Bench v1.11.2%22.6%
Agents
DTBench87.7%83.2%
Professional work
CorpFin v266.0%62.0%
LegalBench82.5%84.1%
MedCode28.1%44.1%
MedScribe78.7%84.5%
MortgageTax42.6%64.0%
TaxEval v273.1%73.3%
Task length · METR40 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG