Compare · ModelsLive · 2 picked · head to head
GPT-5.2 vs MiniMax M3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.2 wins on 7/11 benchmarks
GPT-5.2 wins 7 of 11 shared benchmarks. Leads in knowledge · general · math.
Category leads
agentic·MiniMax M3arena·MiniMax M3knowledge·GPT-5.2general·GPT-5.2math·GPT-5.2reasoning·GPT-5.2
Hype vs Reality
Attention vs performance
GPT-5.2
#162 by perf·#9 by attention
MiniMax M3
#133 by perf·#12 by attention
Best value
MiniMax M3
11.4x better value than GPT-5.2
GPT-5.2
5.9 pts/$
$7.88/M
MiniMax M3
66.9 pts/$
$0.75/M
Vendor risk
Mixed exposure
One or more vendors flagged
OpenAI
$840.0B·Tier 1
MiniMax
$4.0B·Tier 1
Head to head
11 benchmarks · 2 models
GPT-5.2MiniMax M3
APEX-Agents
MiniMax M3 leads by +3.4
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-5.2
34.3
MiniMax M3
37.7
Chatbot Arena Elo · Coding
MiniMax M3 leads by +66.6
GPT-5.2
1415.5
MiniMax M3
1482.0
Chatbot Arena Elo · Overall
MiniMax M3 leads by +4.5
GPT-5.2
1435.6
MiniMax M3
1440.1
Chess Puzzles
GPT-5.2 leads by +32.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5.2
45.3
MiniMax M3
12.7
Dtbench
GPT-5.2 leads by +20.0
GPT-5.2
84.9
MiniMax M3
64.9
GPQA diamond
GPT-5.2 leads by +0.7
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5.2
92.2
MiniMax M3
91.5
Lmca
GPT-5.2 leads by +12.0
GPT-5.2
51.7
MiniMax M3
39.6
Mystery Game Puzzles
GPT-5.2 leads by +15.2
GPT-5.2
15.2
MiniMax M3
0.0
OTIS Mock AIME 2024-2025
GPT-5.2 leads by +25.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5.2
96.1
MiniMax M3
71.1
Proofbench
MiniMax M3 leads by +3.0
GPT-5.2
15.0
MiniMax M3
18.0
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-5.2
35.0
MiniMax M3
35.0
Full benchmark table
| Benchmark | GPT-5.2 | MiniMax M3 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 34.3 | 37.7 |
Chatbot Arena Elo · Coding | 1415.5 | 1482.0 |
Chatbot Arena Elo · Overall | 1435.6 | 1440.1 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 45.3 | 12.7 |
Dtbench | 84.9 | 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. | 92.2 | 91.5 |
Lmca | 51.7 | 39.6 |
Mystery Game Puzzles | 15.2 | 0.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 96.1 | 71.1 |
Proofbench | 15.0 | 18.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 35.0 | 35.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.75 | $14.00 | 400K tokens (~200 books) | $48.13 | |
| $0.30 | $1.20 | 1.0M tokens (~524 books) | $5.25 |