The Model Index
Up to four models

Hy4 preview vs Gemini 3.8 Flash

On the index (GPT-4 = 100), Hy4 preview scores 173 and Gemini 3.8 Flash 173. 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 Hy4 preview
Presets
Hy4 preview
173154–192
WeightsOpen
ReleasedAug 2026
Price in / out$0.83 / $2.5
Context1.05M
Core tests taken2 of 9
Gemini 3.8 Flash
173157–189
WeightsClosed
ReleasedSep 2026
Price in / out$0.82 / $4.13
Context1.05M
Core tests taken7 of 9

Hy4 preview and Gemini 3.8 Flash are too close to call (0 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 1.3× less.

Test by testthird-party results

Hy4 previewGemini 3.8 Flash
0%25%50%75%100%MATHSProofBench v1.1ProofBench v1.1CODINGTerminal-Bench 4.0Terminal-Bench 4.0Code MigrationCode MigrationCyberBench v1.1CyberBench v1.1IOIIOIProgramBenchProgramBenchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSBioMysteryBenchBioMysteryBenchSRE BenchSRE BenchPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBHLAB-Vals-1.1HLAB-Vals-1.1LegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribePublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent Bench
Every result as a table
TestHy4 previewGemini 3.8 Flash
Maths
ProofBench v1.175.0%48.0%
Coding
Terminal-Bench 4.039.4%19.7%
Code Migration47.4%36.5%
CyberBench v1.165.4%43.8%
IOI59.3%56.9%
ProgramBench0.0%1.0%
Vibe Code Bench v1.181.0%78.6%
Agents
BioMysteryBench69.3%62.2%
SRE Bench2.3%11.1%
Professional work
Finance Agent (v2)55.1%61.4%
EMB58.1%72.2%
HLAB-Vals-1.112.5%12.1%
LegalBench83.8%87.0%
Legal Research Bench45.2%38.9%
MedCode43.3%48.1%
MedScribe83.6%84.5%
Public Benefits Bench v1.168.6%65.3%
Tax Agent Bench34.4%32.1%

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

This page as a chartDownload PNG