The Model Index
Up to four models

GLM-5.3-Flash vs Gemini 3 Pro

On the index (GPT-4 = 100), GLM-5.3-Flash scores 161 and Gemini 3 Pro 160. 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
Gemini 3 Pro
160145–176
WeightsClosed
ReleasedNov 2025
Price in / out–
Context–
Core tests taken5 of 9

GLM-5.3-Flash and Gemini 3 Pro are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests.

Test by testthird-party results

GLM-5.3-FlashGemini 3 Pro
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 ProMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL WORKLegalBenchLegalBenchMedScribeMedScribeTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGLM-5.3-FlashGemini 3 Pro
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.1%92.6%
GPQA Diamond (Vals AI)86.4%91.7%
MMLU Pro86.1%90.1%
MMMU Pro86.0%87.5%
Maths
AIME-style maths (OTIS mock)93.9%91.4%
Coding
LiveCodeBench80.5%86.4%
SWE-bench92.0%76.4%
Vibe Code Bench v1.130.8%14.3%
Professional work
LegalBench83.9%87.0%
MedScribe88.9%72.0%
TaxEval v275.6%72.6%
Novel problems
ARC-AGI-265.8%54.0%
ARC-AGI-191.0%75.0%
Task length · METR43 sec

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

This page as a chartDownload PNG