Compare · ModelsLive · 2 picked · head to head
MiniMax M3 vs Qwen3.5 397B A17B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
MiniMax M3 wins on 5/5 benchmarks
MiniMax M3 wins 5 of 5 shared benchmarks. Leads in speed · arena.
Category leads
speed·MiniMax M3arena·MiniMax M3
Hype vs Reality
Attention vs performance
MiniMax M3
#19 by perf·no signal
Qwen3.5 397B A17B
#5 by perf·no signal
Best value
MiniMax M3
1.7x better value than Qwen3.5 397B A17B
MiniMax M3
93.3 pts/$
$0.75/M
Qwen3.5 397B A17B
55.3 pts/$
$1.42/M
Vendor risk
Mixed exposure
One or more vendors flagged
MiniMax
$4.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
5 benchmarks · 2 models
MiniMax M3Qwen3.5 397B A17B
Artificial Analysis · Agentic Index
MiniMax M3 leads by +15.5
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
MiniMax M3
35.4
Qwen3.5 397B A17B
19.9
Artificial Analysis · Coding Index
MiniMax M3 leads by +10.4
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
MiniMax M3
58.6
Qwen3.5 397B A17B
48.2
Artificial Analysis · Quality Index
MiniMax M3 leads by +10.8
MiniMax M3
44.4
Qwen3.5 397B A17B
33.7
Chatbot Arena Elo · Coding
MiniMax M3 leads by +110.4
MiniMax M3
1504.9
Qwen3.5 397B A17B
1394.5
Chatbot Arena Elo · Overall
MiniMax M3 leads by +4.5
MiniMax M3
1448.2
Qwen3.5 397B A17B
1443.7
Full benchmark table
| Benchmark | MiniMax M3 | Qwen3.5 397B A17B |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 35.4 | 19.9 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 58.6 | 48.2 |
Artificial Analysis · Quality Index | 44.4 | 33.7 |
Chatbot Arena Elo · Coding | 1504.9 | 1394.5 |
Chatbot Arena Elo · Overall | 1448.2 | 1443.7 |
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 | |
| $0.39 | $2.45 | 256K tokens (~128 books) | $9.01 |