The Model Index
Up to four models

Gemini 3.8 Flash vs GPT-5.5

On the index (GPT-4 = 100), Gemini 3.8 Flash scores 173 and GPT-5.5 172. 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 3.8 Flash
Presets
Gemini 3.8 Flash
173157–189
WeightsClosed
ReleasedSep 2026
Price in / out$0.82 / $4.13
Context1.05M
Core tests taken7 of 9
GPT-5.5
172156–188
WeightsClosed
ReleasedApr 2026
Price in / out$5.0 / $30
Context1.05M
Core tests taken6 of 9

Gemini 3.8 Flash and GPT-5.5 are too close to call (1 point apart, within the uncertainty), ahead on 4 of 5 shared core tests, and costs 6.8× less.

Test by testthird-party results

Gemini 3.8 FlashGPT-5.5
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 ProSimpleBenchSimpleBenchSimpleQA 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 BenchCODINGCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEMirrorCodeMirrorCodeWeirdMLWeirdMLAGENTSAPEX-AgentsAPEX-AgentsSkillsBenchSkillsBenchSRE BenchSRE BenchDTBenchDTBenchFurniture assemblyFurniture assemblyLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxPublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent BenchTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1ARC-AGI-3ARC-AGI-3
Every result as a table
TestGemini 3.8 FlashGPT-5.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)95.4%94.0%
GPQA Diamond (Vals AI)94.4%93.2%
MMLU Pro90.2%88.1%
MMMU Pro89.1%88.3%
SimpleBench82.4%69.0%
SimpleQA Verified69.7%63.0%
Maths
FrontierMath (tiers 1-3)68.4%85.3%
AIME-style maths (OTIS mock)98.9%100.0%
Chess puzzles58.0%63.0%
FrontierMath (tier 4)21.9%72.5%
Surface Evolver Bench76.9%88.1%
Coding
Code Migration36.5%45.2%
LiveCodeBench89.5%85.3%
ProgramBench1.0%0.5%
SWE-bench80.0%82.6%
Vibe Code Bench v1.178.6%69.8%
DeepSWE73.8%67.0%
MirrorCode38.9%23.3%
WeirdML84.8%84.9%
Agents
APEX-Agents64.3%55.1%
SkillsBench58.0%62.2%
SRE Bench11.1%3.8%
DTBench95.7%96.0%
Furniture assembly31.7%44.2%
LMCA52.9%54.3%
Mystery game puzzles47.0%56.0%
Professional work
Finance Agent (v2)61.4%51.8%
EMB72.2%64.5%
LegalBench87.0%86.5%
Legal Research Bench38.9%40.4%
MedCode48.1%49.1%
MedScribe84.5%86.9%
MortgageTax65.3%68.8%
Public Benefits Bench v1.165.3%60.9%
Tax Agent Bench32.1%21.8%
TaxEval v274.5%75.0%
Novel problems
ARC-AGI-289.2%85.0%
ARC-AGI-198.5%95.0%
ARC-AGI-310.4%0.4%

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

This page as a chartDownload PNG