Compare · ModelsLive · 2 picked · head to head
Qwen3.6 35B A3B vs Qwen3.7 Plus
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3.7 Plus wins on 15/20 benchmarks
Qwen3.7 Plus wins 15 of 20 shared benchmarks. Leads in speed · general · math.
Category leads
speed·Qwen3.7 Plusknowledge·Qwen3.6 35B A3Bgeneral·Qwen3.7 Plusmath·Qwen3.7 Plus
Hype vs Reality
Attention vs performance
Qwen3.6 35B A3B
#181 by perf·#2 by attention
Qwen3.7 Plus
#189 by perf·#2 by attention
Best value
Qwen3.6 35B A3B
1.4x better value than Qwen3.7 Plus
Qwen3.6 35B A3B
72.7 pts/$
$0.57/M
Qwen3.7 Plus
51.5 pts/$
$0.80/M
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
20 benchmarks · 2 models
Qwen3.6 35B A3BQwen3.7 Plus
Artificial Analysis · Agentic Index
Qwen3.6 35B A3B leads by +0.6
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?"
Qwen3.6 35B A3B
21.4
Qwen3.7 Plus
20.8
Artificial Analysis · Coding Index
Qwen3.7 Plus leads by +14.0
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.
Qwen3.6 35B A3B
41.9
Qwen3.7 Plus
55.9
Artificial Analysis · CritPt
Qwen3.7 Plus leads by +8.8
Qwen3.6 35B A3B
0.3
Qwen3.7 Plus
9.1
Artificial Analysis · GDPval
Qwen3.6 35B A3B leads by +6.2
Qwen3.6 35B A3B
19.6
Qwen3.7 Plus
13.4
Artificial Analysis · GPQA Diamond
Qwen3.7 Plus leads by +5.9
Qwen3.6 35B A3B
84.1
Qwen3.7 Plus
90.0
Artificial Analysis · Humanity's Last Exam
Qwen3.7 Plus leads by +13.4
Qwen3.6 35B A3B
22.2
Qwen3.7 Plus
35.6
Artificial Analysis · IFBench
Qwen3.7 Plus leads by +13.6
Qwen3.6 35B A3B
64.4
Qwen3.7 Plus
78.0
Artificial Analysis · Long Context Reasoning
Qwen3.7 Plus leads by +1.3
Qwen3.6 35B A3B
71.7
Qwen3.7 Plus
73.0
Artificial Analysis · MMMU Pro
Qwen3.7 Plus leads by +5.5
Qwen3.6 35B A3B
75.0
Qwen3.7 Plus
80.5
Artificial Analysis · Quality Index
Qwen3.7 Plus leads by +6.9
Qwen3.6 35B A3B
18.2
Qwen3.7 Plus
25.2
Artificial Analysis · SciCode
Qwen3.7 Plus leads by +9.5
Qwen3.6 35B A3B
36.6
Qwen3.7 Plus
46.1
Artificial Analysis · tau2-Bench Telecom
Qwen3.6 35B A3B leads by +2.3
Qwen3.6 35B A3B
95.3
Qwen3.7 Plus
93.0
Artificial Analysis · Terminal-Bench Hard
Qwen3.7 Plus leads by +12.2
Qwen3.6 35B A3B
34.8
Qwen3.7 Plus
47.0
Chess Puzzles
Qwen3.6 35B A3B leads by +2.1
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Qwen3.6 35B A3B
22.1
Qwen3.7 Plus
20.0
Dtbench
Qwen3.7 Plus leads by +16.9
Qwen3.6 35B A3B
56.5
Qwen3.7 Plus
73.3
FrontierMath-Tiers-1-3-v2-Private
Qwen3.7 Plus leads by +14.0
Qwen3.6 35B A3B
20.4
Qwen3.7 Plus
34.4
GPQA diamond
Qwen3.7 Plus leads by +4.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen3.6 35B A3B
79.8
Qwen3.7 Plus
83.8
Lmca
Qwen3.7 Plus leads by +9.3
Qwen3.6 35B A3B
34.9
Qwen3.7 Plus
44.2
Mystery Game Puzzles
Qwen3.6 35B A3B leads by +5.5
Qwen3.6 35B A3B
14.1
Qwen3.7 Plus
8.6
OTIS Mock AIME 2024-2025
Qwen3.7 Plus leads by +6.7
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Qwen3.6 35B A3B
86.7
Qwen3.7 Plus
93.3
Full benchmark table
| Benchmark | Qwen3.6 35B A3B | Qwen3.7 Plus |
|---|---|---|
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?" | 21.4 | 20.8 |
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. | 41.9 | 55.9 |
Artificial Analysis · CritPt | 0.3 | 9.1 |
Artificial Analysis · GDPval | 19.6 | 13.4 |
Artificial Analysis · GPQA Diamond | 84.1 | 90.0 |
Artificial Analysis · Humanity's Last Exam | 22.2 | 35.6 |
Artificial Analysis · IFBench | 64.4 | 78.0 |
Artificial Analysis · Long Context Reasoning | 71.7 | 73.0 |
Artificial Analysis · MMMU Pro | 75.0 | 80.5 |
Artificial Analysis · Quality Index | 18.2 | 25.2 |
Artificial Analysis · SciCode | 36.6 | 46.1 |
Artificial Analysis · tau2-Bench Telecom | 95.3 | 93.0 |
Artificial Analysis · Terminal-Bench Hard | 34.8 | 47.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 22.1 | 20.0 |
Dtbench | 56.5 | 73.3 |
FrontierMath-Tiers-1-3-v2-Private | 20.4 | 34.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 79.8 | 83.8 |
Lmca | 34.9 | 44.2 |
Mystery Game Puzzles | 14.1 | 8.6 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 86.7 | 93.3 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.15 | $1.00 | 262K tokens (~131 books) | $3.63 | |
| $0.32 | $1.28 | 1.0M tokens (~500 books) | $5.60 |