Compare · ModelsLive · 2 picked · head to head
DeepSeek V3 vs MiniMax M3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
MiniMax M3 wins on 6/6 benchmarks
MiniMax M3 wins 6 of 6 shared benchmarks. Leads in arena · general · knowledge.
Category leads
arena·MiniMax M3general·MiniMax M3knowledge·MiniMax M3math·MiniMax M3reasoning·MiniMax M3
Hype vs Reality
Attention vs performance
DeepSeek V3
#70 by perf·no signal
MiniMax M3
#124 by perf·#11 by attention
Best value
DeepSeek V3
1.3x better value than MiniMax M3
DeepSeek V3
87.2 pts/$
$0.64/M
MiniMax M3
66.5 pts/$
$0.75/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
MiniMax
$4.0B·Tier 1
Head to head
6 benchmarks · 2 models
DeepSeek V3MiniMax M3
Chatbot Arena Elo · Overall
MiniMax M3 leads by +81.6
DeepSeek V3
1358.4
MiniMax M3
1440.1
Dtbench
MiniMax M3 leads by +23.5
DeepSeek V3
41.3
MiniMax M3
64.9
GPQA diamond
MiniMax M3 leads by +45.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V3
42.0
MiniMax M3
87.9
Lmca
MiniMax M3 leads by +21.4
DeepSeek V3
18.2
MiniMax M3
39.6
OTIS Mock AIME 2024-2025
MiniMax M3 leads by +55.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V3
15.8
MiniMax M3
71.1
SimpleBench
MiniMax M3 leads by +32.3
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
DeepSeek V3
2.7
MiniMax M3
35.0
Full benchmark table
| Benchmark | DeepSeek V3 | MiniMax M3 |
|---|---|---|
Chatbot Arena Elo · Overall | 1358.4 | 1440.1 |
Dtbench | 41.3 | 64.9 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 42.0 | 87.9 |
Lmca | 18.2 | 39.6 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 15.8 | 71.1 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 2.7 | 35.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.26 | $1.03 | 164K tokens (~82 books) | $4.50 | |
| $0.30 | $1.20 | 1.0M tokens (~524 books) | $5.25 |