The Model Index
Up to four models

DeepSeek-V3 (Mar 2025) vs Gemini 2.0 Flash Thinking (Jan 2025)

On the index (GPT-4 = 100), DeepSeek-V3 (Mar 2025) scores 124 and Gemini 2.0 Flash Thinking (Jan 2025) 123. 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 (Mar 2025)
Presets
DeepSeek-V3 (Mar 2025)
124108–140
WeightsOpen
ReleasedMar 2025
Price in / out$0.29 / $1.14
Context164K
Core tests taken2 of 9
Gemini 2.0 Flash Thinking (Jan 2025)
123107–139
WeightsClosed
ReleasedJan 2025
Price in / out–
Context–
Core tests taken2 of 9

DeepSeek-V3 (Mar 2025) and Gemini 2.0 Flash Thinking (Jan 2025) are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

DeepSeek-V3 (Mar 2025)Gemini 2.0 Flash Thinking (Jan 2025)
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)Fiction.LiveBenchFiction.LiveBenchSimpleBenchSimpleBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGAider PolyglotAider Polyglot
Every result as a table
TestDeepSeek-V3 (Mar 2025)Gemini 2.0 Flash Thinking (Jan 2025)
Reasoning & knowledge
GPQA Diamond (Epoch AI)67.6%57.1%
Fiction.LiveBench50.0%52.8%
SimpleBench27.2%30.7%
Maths
AIME-style maths (OTIS mock)37.8%57.8%
Coding
Aider Polyglot55.1%18.2%
Task length · METR30 sec

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

This page as a chartDownload PNG