Compare · ModelsLive · 2 picked · head to head
Qwen3.5 397B A17B vs Qwen3.7 Max
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3.7 Max wins on 10/10 benchmarks
Qwen3.7 Max wins 10 of 10 shared benchmarks. Leads in speed · knowledge · general.
Category leads
speed·Qwen3.7 Maxknowledge·Qwen3.7 Maxgeneral·Qwen3.7 Maxmath·Qwen3.7 Max
Hype vs Reality
Attention vs performance
Qwen3.5 397B A17B
#48 by perf·#2 by attention
Qwen3.7 Max
#41 by perf·#2 by attention
Best value
Qwen3.5 397B A17B
1.2x better value than Qwen3.7 Max
Qwen3.5 397B A17B
29.6 pts/$
$2.02/M
Qwen3.7 Max
24.5 pts/$
$2.50/M
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
10 benchmarks · 2 models
Qwen3.5 397B A17BQwen3.7 Max
Artificial Analysis · Agentic Index
Qwen3.7 Max leads by +10.7
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?"
Qwen3.5 397B A17B
19.9
Qwen3.7 Max
30.6
Artificial Analysis · Coding Index
Qwen3.7 Max leads by +17.8
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.
Qwen3.5 397B A17B
48.2
Qwen3.7 Max
66.0
Artificial Analysis · Quality Index
Qwen3.7 Max leads by +24.6
Qwen3.5 397B A17B
21.4
Qwen3.7 Max
46.0
Chess Puzzles
Qwen3.7 Max leads by +6.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Qwen3.5 397B A17B
8.5
Qwen3.7 Max
14.8
Dtbench
Qwen3.7 Max leads by +8.0
Qwen3.5 397B A17B
79.1
Qwen3.7 Max
87.1
FrontierMath-Tiers-1-3-v2-Private
Qwen3.7 Max leads by +33.3
Qwen3.5 397B A17B
31.2
Qwen3.7 Max
64.6
GPQA diamond
Qwen3.7 Max leads by +6.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen3.5 397B A17B
81.8
Qwen3.7 Max
87.9
Lmca
Qwen3.7 Max leads by +7.2
Qwen3.5 397B A17B
44.6
Qwen3.7 Max
51.8
Mystery Game Puzzles
Qwen3.7 Max leads by +15.4
Qwen3.5 397B A17B
9.7
Qwen3.7 Max
25.1
OTIS Mock AIME 2024-2025
Qwen3.7 Max leads by +6.7
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Qwen3.5 397B A17B
88.9
Qwen3.7 Max
95.5
Full benchmark table
| Benchmark | Qwen3.5 397B A17B | Qwen3.7 Max |
|---|---|---|
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?" | 19.9 | 30.6 |
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. | 48.2 | 66.0 |
Artificial Analysis · Quality Index | 21.4 | 46.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 8.5 | 14.8 |
Dtbench | 79.1 | 87.1 |
FrontierMath-Tiers-1-3-v2-Private | 31.2 | 64.6 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 81.8 | 87.9 |
Lmca | 44.6 | 51.8 |
Mystery Game Puzzles | 9.7 | 25.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 88.9 | 95.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.55 | $3.50 | 262K tokens (~131 books) | $12.88 | |
| $1.25 | $3.75 | 1.0M tokens (~500 books) | $18.75 |