Compare · ModelsLive · 2 picked · head to head
MiniMax M3 vs Qwen3 235B A22B Thinking 2507
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
MiniMax M3 wins on 12/15 benchmarks
MiniMax M3 wins 12 of 15 shared benchmarks. Leads in arena · knowledge · general.
Category leads
arena·MiniMax M3knowledge·MiniMax M3general·MiniMax M3coding·MiniMax M3reasoning·MiniMax M3language·MiniMax M3math·MiniMax M3
Hype vs Reality
Attention vs performance
MiniMax M3
#124 by perf·#11 by attention
Qwen3 235B A22B Thinking 2507
#99 by perf·#2 by attention
Best value
MiniMax M3
1.6x better value than Qwen3 235B A22B Thinking 2507
MiniMax M3
66.5 pts/$
$0.75/M
Qwen3 235B A22B Thinking 2507
41.9 pts/$
$1.26/M
Vendor risk
Mixed exposure
One or more vendors flagged
MiniMax
$4.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
15 benchmarks · 2 models
MiniMax M3Qwen3 235B A22B Thinking 2507
Chatbot Arena Elo · Overall
MiniMax M3 leads by +40.1
MiniMax M3
1440.1
Qwen3 235B A22B Thinking 2507
1400.0
Chess Puzzles
MiniMax M3 leads by +2.1
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
MiniMax M3
9.5
Qwen3 235B A22B Thinking 2507
7.4
Dtbench
Qwen3 235B A22B Thinking 2507 leads by +2.2
MiniMax M3
64.9
Qwen3 235B A22B Thinking 2507
67.1
GPQA diamond
MiniMax M3 leads by +14.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
MiniMax M3
87.9
Qwen3 235B A22B Thinking 2507
73.4
LiveBench · Agentic Coding
MiniMax M3 leads by +53.3
MiniMax M3
60.0
Qwen3 235B A22B Thinking 2507
6.7
LiveBench · Coding
Qwen3 235B A22B Thinking 2507 leads by +0.8
MiniMax M3
68.2
Qwen3 235B A22B Thinking 2507
69.0
LiveBench · Data Analysis
MiniMax M3 leads by +24.0
MiniMax M3
76.2
Qwen3 235B A22B Thinking 2507
52.2
LiveBench · If
MiniMax M3 leads by +16.9
MiniMax M3
57.5
Qwen3 235B A22B Thinking 2507
40.6
LiveBench · Language
MiniMax M3 leads by +7.3
MiniMax M3
76.8
Qwen3 235B A22B Thinking 2507
69.5
LiveBench · Mathematics
MiniMax M3 leads by +3.6
MiniMax M3
77.0
Qwen3 235B A22B Thinking 2507
73.4
LiveBench · Overall
MiniMax M3 leads by +17.0
MiniMax M3
70.0
Qwen3 235B A22B Thinking 2507
53.0
LiveBench · Reasoning
MiniMax M3 leads by +15.1
MiniMax M3
74.5
Qwen3 235B A22B Thinking 2507
59.4
Lmca
MiniMax M3 leads by +5.2
MiniMax M3
39.6
Qwen3 235B A22B Thinking 2507
34.5
Mystery Game Puzzles
MiniMax M3
0.0
Qwen3 235B A22B Thinking 2507
0.0
OTIS Mock AIME 2024-2025
Qwen3 235B A22B Thinking 2507 leads by +15.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
MiniMax M3
71.1
Qwen3 235B A22B Thinking 2507
86.7
Full benchmark table
| Benchmark | MiniMax M3 | Qwen3 235B A22B Thinking 2507 |
|---|---|---|
Chatbot Arena Elo · Overall | 1440.1 | 1400.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 9.5 | 7.4 |
Dtbench | 64.9 | 67.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.9 | 73.4 |
LiveBench · Agentic Coding | 60.0 | 6.7 |
LiveBench · Coding | 68.2 | 69.0 |
LiveBench · Data Analysis | 76.2 | 52.2 |
LiveBench · If | 57.5 | 40.6 |
LiveBench · Language | 76.8 | 69.5 |
LiveBench · Mathematics | 77.0 | 73.4 |
LiveBench · Overall | 70.0 | 53.0 |
LiveBench · Reasoning | 74.5 | 59.4 |
Lmca | 39.6 | 34.5 |
Mystery Game Puzzles | 0.0 | 0.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 71.1 | 86.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.30 | $1.20 | 1.0M tokens (~524 books) | $5.25 | |
| $0.23 | $2.30 | 131K tokens (~66 books) | $7.47 |
People also compared