The Model Index
Up to four models

o4-mini vs DeepSeek-V3.2

On the index (GPT-4 = 100), o4-mini scores 141 and DeepSeek-V3.2 141. 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 o4-mini
Presets
o4-mini
141126–157
WeightsClosed
ReleasedApr 2025
Price in / out–
Context–
Core tests taken5 of 9
DeepSeek-V3.2
141125–157
WeightsOpen
ReleasedDec 2025
Price in / out$0.26 / $0.38
Context164K
Core tests taken2 of 9

o4-mini and DeepSeek-V3.2 are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

o4-miniDeepSeek-V3.2
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGAider PolyglotAider PolyglotAGENTSDTBenchDTBenchLMCALMCA
Every result as a table
Testo4-miniDeepSeek-V3.2
Reasoning & knowledge
GPQA Diamond (Epoch AI)79.6%83.4%
Maths
AIME-style maths (OTIS mock)81.7%87.8%
FrontierMath (2025 set)24.8%22.1%
FrontierMath tier 4 (2025 set)6.3%2.1%
Coding
Aider Polyglot72.0%74.2%
Agents
DTBench77.6%85.6%
LMCA26.5%28.8%
Task length · METR38 sec

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

This page as a chartDownload PNG