The Model Index
Up to four models

Gemini 3.5 Flash vs GLM-5.2

On the index (GPT-4 = 100), Gemini 3.5 Flash scores 162 and GLM-5.2 154. 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 3.5 Flash
Presets
Gemini 3.5 Flash
162146–177
WeightsClosed
ReleasedMay 2026
Price in / out$1.5 / $9.0
Context1.05M
Core tests taken7 of 9
GLM-5.2
154138–169
WeightsOpen
ReleasedJun 2026
Price in / out$0.0070 / $6.8
Context1.05M
Core tests taken6 of 9

Gemini 3.5 Flash leads GLM-5.2 by 8 points, ahead on 5 of 6 shared core tests, at 2.0× the price.

Test by testthird-party results

Gemini 3.5 FlashGLM-5.2
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProEBR-benchEBR-benchSimpleBenchSimpleBenchSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (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)Surface Evolver BenchSurface Evolver BenchCODINGSWE-bench VerifiedSWE-bench VerifiedCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEWeirdMLWeirdMLAGENTSAPEX-AgentsAPEX-AgentsSkillsBenchSkillsBenchDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGemini 3.5 FlashGLM-5.2
Reasoning & knowledge
GPQA Diamond (Epoch AI)92.8%91.9%
GPQA Diamond (Vals AI)92.7%85.6%
MMLU Pro89.5%86.7%
EBR-bench4.8%9.5%
SimpleBench76.7%58.8%
SimpleQA Verified66.2%34.2%
Maths
FrontierMath (tiers 1-3)62.8%59.2%
AIME-style maths (OTIS mock)95.6%86.4%
Chess puzzles45.0%22.0%
FrontierMath (tier 4)26.8%29.3%
Surface Evolver Bench58.1%55.6%
Coding
SWE-bench Verified79.3%78.7%
Code Migration26.8%37.9%
LiveCodeBench87.6%69.5%
ProgramBench0.0%0.5%
SWE-bench78.8%82.8%
Vibe Code Bench v1.148.7%64.0%
DeepSWE37.4%43.8%
WeirdML62.6%70.1%
Agents
APEX-Agents27.5%45.2%
SkillsBench52.7%45.1%
DTBench94.7%93.6%
LMCA47.1%45.8%
Mystery game puzzles32.0%19.0%
Professional work
Finance Agent (v2)57.9%49.7%
CorpFin v264.7%66.1%
EMB63.5%61.5%
LegalBench83.6%84.1%
Legal Research Bench30.8%31.3%
MedCode55.8%40.8%
MedScribe76.6%83.5%
TaxEval v274.4%73.3%
Novel problems
ARC-AGI-272.1%22.8%
ARC-AGI-192.5%77.0%

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

This page as a chartDownload PNG