The Model Index
Up to four models

GLM-5.3 vs Gemini 3.5 Flash-Lite

On the index (GPT-4 = 100), GLM-5.3 scores 168 and Gemini 3.5 Flash-Lite 141. 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
Presets
GLM-5.3
168152–184
WeightsOpen
ReleasedAug 2026
Price in / out$0.070 / $1.4
Context1.05M
Core tests taken5 of 9
Gemini 3.5 Flash-Lite
141125–156
WeightsClosed
ReleasedJul 2026
Price in / out$0.30 / $2.5
Context1.05M
Core tests taken5 of 9

GLM-5.3 leads Gemini 3.5 Flash-Lite by 28 points, ahead on 4 of 4 shared core tests, and costs 2.1× less.

Test by testthird-party results

GLM-5.3Gemini 3.5 Flash-Lite
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU 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 MigrationCyberBench v1.1CyberBench v1.1LiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdMLAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribePublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent BenchTaxEval v2TaxEval v2
Every result as a table
TestGLM-5.3Gemini 3.5 Flash-Lite
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.9%83.3%
GPQA Diamond (Vals AI)88.1%83.8%
MMLU Pro86.8%85.8%
Maths
FrontierMath (tiers 1-3)68.8%26.0%
AIME-style maths (OTIS mock)91.1%71.1%
Chess puzzles37.0%21.0%
FrontierMath (tier 4)29.3%0.0%
Coding
Code Migration44.2%6.2%
CyberBench v1.172.1%59.1%
LiveCodeBench80.5%79.0%
ProgramBench1.5%0.0%
SWE-bench95.4%75.0%
Vibe Code Bench v1.178.1%37.2%
WeirdML75.4%39.0%
Agents
APEX-Agents56.6%29.3%
DTBench87.7%83.5%
LMCA55.5%37.6%
Mystery game puzzles33.0%19.0%
Professional work
Finance Agent (v2)55.8%47.4%
EMB56.3%43.2%
LegalBench84.8%84.1%
Legal Research Bench49.0%13.9%
MedCode42.9%43.5%
MedScribe88.8%70.9%
Public Benefits Bench v1.168.5%51.8%
Tax Agent Bench43.3%7.2%
TaxEval v272.4%72.6%

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

This page as a chartDownload PNG