The Model Index
Up to four models

Grok 4.20 vs Qwen3.8-27B

On the index (GPT-4 = 100), Grok 4.20 scores 156 and Qwen3.8-27B 155. 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 4.20
Presets
Grok 4.20
156140–172
WeightsClosed
ReleasedFeb 2026
Price in / out$1.25 / $2.5
Context2M
Core tests taken4 of 9
Qwen3.8-27B
155139–171
WeightsOpen
ReleasedAug 2026
Price in / out$0.060 / $2.2
Context1.02M
Core tests taken3 of 9

Grok 4.20 and Qwen3.8-27B are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, at 2.6× the price.

Test by testthird-party results

Grok 4.20Qwen3.8-27B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProCODINGCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSDTBenchDTBenchLMCALMCAPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTax Agent BenchTax Agent BenchTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGrok 4.20Qwen3.8-27B
Reasoning & knowledge
GPQA Diamond (Vals AI)88.6%88.9%
MMLU Pro86.3%84.3%
MMMU Pro83.5%83.9%
Coding
Code Migration0.3%14.2%
LiveCodeBench84.3%84.0%
SWE-bench72.2%86.0%
Vibe Code Bench v1.14.1%64.8%
Agents
DTBench90.1%88.0%
LMCA38.7%41.4%
Professional work
Finance Agent (v2)28.5%48.5%
EMB11.7%59.7%
LegalBench77.7%82.4%
Legal Research Bench13.9%36.1%
MedCode32.2%28.7%
MedScribe63.4%83.9%
MortgageTax45.4%64.9%
Tax Agent Bench7.0%30.9%
TaxEval v274.1%70.9%
Novel problems
ARC-AGI-265.1%42.4%
ARC-AGI-189.5%87.5%

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

This page as a chartDownload PNG