The Model Index
Up to four models

Hy4 preview vs DeepSeek V4.1 Flash 1017

On the index (GPT-4 = 100), Hy4 preview scores 173 and DeepSeek V4.1 Flash 1017 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 Hy4 preview
Presets
Hy4 preview
173154–192
WeightsOpen
ReleasedAug 2026
Price in / out$0.83 / $2.5
Context1.05M
Core tests taken2 of 9
DeepSeek V4.1 Flash 1017
172156–188
WeightsOpen
ReleasedOct 2026
Price in / out$0.036 / $0.50
Context1.05M
Core tests taken6 of 9

Hy4 preview and DeepSeek V4.1 Flash 1017 are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, at 8.2× the price.

Test by testthird-party results

Hy4 previewDeepSeek V4.1 Flash 1017
0%25%50%75%100%CODINGTerminal-Bench 4.0Terminal-Bench 4.0Code MigrationCode MigrationVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBHLAB-Vals-1.1HLAB-Vals-1.1Legal Research BenchLegal Research BenchTax Agent BenchTax Agent Bench
Every result as a table
TestHy4 previewDeepSeek V4.1 Flash 1017
Coding
Terminal-Bench 4.039.4%31.8%
Code Migration47.4%44.2%
Vibe Code Bench v1.181.0%87.7%
Professional work
Finance Agent (v2)55.1%57.0%
EMB58.1%61.8%
HLAB-Vals-1.112.5%14.2%
Legal Research Bench45.2%45.2%
Tax Agent Bench34.4%44.4%

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

This page as a chartDownload PNG