The Model Index
Up to four models

GPT-5.5 vs DeepSeek V4.1 Flash 1017

On the index (GPT-4 = 100), GPT-5.5 scores 172 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 GPT-5.5
Presets
GPT-5.5
172156–188
WeightsClosed
ReleasedApr 2026
Price in / out$5.0 / $30
Context1.05M
Core tests taken6 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

GPT-5.5 and DeepSeek V4.1 Flash 1017 are too close to call (0 points apart, within the uncertainty), ahead on 3 of 5 shared core tests, at 74× the price.

Test by testthird-party results

GPT-5.5DeepSeek V4.1 Flash 1017
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA 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)CODINGCode MigrationCode MigrationVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSAPEX-AgentsAPEX-AgentsMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegal Research BenchLegal Research BenchTax Agent BenchTax Agent BenchNOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1ARC-AGI-3ARC-AGI-3
Every result as a table
TestGPT-5.5DeepSeek V4.1 Flash 1017
Reasoning & knowledge
GPQA Diamond (Epoch AI)94.0%93.2%
SimpleQA Verified63.0%42.5%
Maths
FrontierMath (tiers 1-3)85.3%71.2%
AIME-style maths (OTIS mock)100.0%99.4%
Chess puzzles63.0%46.0%
FrontierMath (tier 4)72.5%46.3%
Coding
Code Migration45.2%44.2%
Vibe Code Bench v1.169.8%87.7%
Agents
APEX-Agents55.1%69.8%
Mystery game puzzles56.0%49.0%
Professional work
Finance Agent (v2)51.8%57.0%
EMB64.5%61.8%
Legal Research Bench40.4%45.2%
Tax Agent Bench21.8%44.4%
Novel problems
ARC-AGI-285.0%78.1%
ARC-AGI-195.0%94.5%
ARC-AGI-30.4%0.2%

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

This page as a chartDownload PNG