The Model Index
Up to four models

DeepSeek-V3.2 vs Gemini 3.5 Flash-Lite

On the index (GPT-4 = 100), DeepSeek-V3.2 scores 141 and Gemini 3.5 Flash-Lite 141. 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 DeepSeek-V3.2
Presets
DeepSeek-V3.2
141125–157
WeightsOpen
ReleasedDec 2025
Price in / out$0.26 / $0.38
Context164K
Core tests taken2 of 9
Gemini 3.5 Flash-Lite
141125–156
WeightsClosed
ReleasedJul 2026
Price in / out$0.30 / $2.5
Context1.05M
Core tests taken5 of 9

DeepSeek-V3.2 and Gemini 3.5 Flash-Lite are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 2.9× less.

Test by testthird-party results

DeepSeek-V3.2Gemini 3.5 Flash-Lite
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCA
Every result as a table
TestDeepSeek-V3.2Gemini 3.5 Flash-Lite
Reasoning & knowledge
GPQA Diamond (Epoch AI)83.4%83.3%
Maths
AIME-style maths (OTIS mock)87.8%71.1%
Agents
APEX-Agents21.3%29.3%
DTBench85.6%83.5%
LMCA28.8%37.6%

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

This page as a chartDownload PNG