The Model Index
Up to four models

Gemini 3.7 Flash vs GLM-5.3

On the index (GPT-4 = 100), Gemini 3.7 Flash scores 170 and GLM-5.3 168. 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 Gemini 3.7 Flash
Presets
Gemini 3.7 Flash
170154–186
WeightsClosed
ReleasedAug 2026
Price in / out$0.75 / $3.75
Context1.05M
Core tests taken6 of 9
GLM-5.3
168152–184
WeightsOpen
ReleasedAug 2026
Price in / out$0.070 / $1.4
Context1.05M
Core tests taken5 of 9

Gemini 3.7 Flash and GLM-5.3 are too close to call (2 points apart, within the uncertainty), ahead on 4 of 5 shared core tests, at 3.7× the price.

Test by testthird-party results

Gemini 3.7 FlashGLM-5.3
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)ProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGTerminal-Bench 4.0Terminal-Bench 4.0Code MigrationCode MigrationCyberBench v1.1CyberBench v1.1IOIIOILiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEFrontierSWEFrontierSWEAGENTSAPEX-AgentsAPEX-AgentsSkillsBenchSkillsBenchSRE BenchSRE BenchTerminal-Bench-ScienceTerminal-Bench-ScienceDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeTax Agent BenchTax Agent BenchTaxEval v2TaxEval v2
Every result as a table
TestGemini 3.7 FlashGLM-5.3
Reasoning & knowledge
GPQA Diamond (Epoch AI)94.8%90.9%
GPQA Diamond (Vals AI)93.9%88.1%
MMLU Pro90.1%86.8%
SimpleQA Verified69.2%41.0%
Maths
FrontierMath (tiers 1-3)71.6%68.8%
AIME-style maths (OTIS mock)97.2%91.1%
ProofBench v1.158.0%49.0%
Chess puzzles66.0%37.0%
FrontierMath (tier 4)36.6%29.3%
Coding
Terminal-Bench 4.012.1%38.9%
Code Migration34.8%44.2%
CyberBench v1.143.8%72.1%
IOI67.8%68.4%
LiveCodeBench88.6%80.5%
ProgramBench0.0%1.5%
SWE-bench80.8%95.4%
Vibe Code Bench v1.170.4%78.1%
DeepSWE65.5%69.0%
FrontierSWE20.3%30.2%
Agents
APEX-Agents67.8%56.6%
SkillsBench65.9%47.5%
SRE Bench4.6%9.2%
Terminal-Bench-Science7.1%5.7%
DTBench96.8%87.7%
LMCA50.4%55.5%
Mystery game puzzles37.0%33.0%
Professional work
Finance Agent (v2)59.0%55.8%
EMB71.3%56.3%
LegalBench87.3%84.8%
Legal Research Bench34.6%49.0%
MedCode53.4%42.9%
MedScribe83.9%88.8%
Tax Agent Bench22.8%43.3%
TaxEval v274.7%72.4%

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

This page as a chartDownload PNG