The Model Index
Up to four models

GLM-5.3-Flash vs Grok 4.20

On the index (GPT-4 = 100), GLM-5.3-Flash scores 161 and Grok 4.20 156. 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 GLM-5.3-Flash
Presets
GLM-5.3-Flash
161145–177
WeightsOpen
ReleasedAug 2026
Price in / out$0.15 / $0.50
Context1.05M
Core tests taken6 of 9
Grok 4.20
156140–172
WeightsClosed
ReleasedFeb 2026
Price in / out$1.25 / $2.5
Context2M
Core tests taken4 of 9

GLM-5.3-Flash leads Grok 4.20 by 5 points, ahead on 4 of 4 shared core tests, and costs 6.6× less.

Test by testthird-party results

GLM-5.3-FlashGrok 4.20
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedScribeMedScribeTax Agent BenchTax Agent BenchTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGLM-5.3-FlashGrok 4.20
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.1%89.3%
GPQA Diamond (Vals AI)86.4%88.6%
MMLU Pro86.1%86.3%
MMMU Pro86.0%83.5%
Maths
FrontierMath (tiers 1-3)55.8%44.9%
AIME-style maths (OTIS mock)93.9%92.2%
Chess puzzles21.0%29.0%
FrontierMath (tier 4)17.1%17.1%
Coding
Code Migration20.5%0.3%
LiveCodeBench80.5%84.3%
SWE-bench92.0%72.2%
Vibe Code Bench v1.130.8%4.1%
Professional work
Finance Agent (v2)57.9%28.5%
EMB55.9%11.7%
LegalBench83.9%77.7%
Legal Research Bench45.2%13.9%
MedScribe88.9%63.4%
Tax Agent Bench31.6%7.0%
TaxEval v275.6%74.1%
Novel problems
ARC-AGI-265.8%65.1%
ARC-AGI-191.0%89.5%

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

This page as a chartDownload PNG