Compare · ModelsLive · 2 picked · head to head
Claude Opus 4.1 vs Qwen3.6 35B A3B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3.6 35B A3B wins on 5/9 benchmarks
Qwen3.6 35B A3B wins 5 of 9 shared benchmarks. Leads in knowledge · math.
Category leads
knowledge·Qwen3.6 35B A3Bgeneral·Claude Opus 4.1math·Qwen3.6 35B A3Bcoding·Claude Opus 4.1
Hype vs Reality
Attention vs performance
Claude Opus 4.1
#213 by perf·#9 by attention
Qwen3.6 35B A3B
#178 by perf·#2 by attention
Best value
Qwen3.6 35B A3B
89.4x better value than Claude Opus 4.1
Claude Opus 4.1
0.8 pts/$
$45.00/M
Qwen3.6 35B A3B
72.3 pts/$
$0.57/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
9 benchmarks · 2 models
Claude Opus 4.1Qwen3.6 35B A3B
Chess Puzzles
Qwen3.6 35B A3B leads by +20.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Opus 4.1
2.1
Qwen3.6 35B A3B
22.1
Dtbench
Claude Opus 4.1 leads by +10.2
Claude Opus 4.1
66.7
Qwen3.6 35B A3B
56.5
FrontierMath-Tiers-1-3-v2-Private
Qwen3.6 35B A3B leads by +7.7
Claude Opus 4.1
12.6
Qwen3.6 35B A3B
20.4
GPQA diamond
Qwen3.6 35B A3B leads by +10.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 4.1
69.7
Qwen3.6 35B A3B
79.8
Lmca
Claude Opus 4.1 leads by +8.7
Claude Opus 4.1
43.6
Qwen3.6 35B A3B
34.9
Mystery Game Puzzles
Qwen3.6 35B A3B leads by +1.1
Claude Opus 4.1
13.0
Qwen3.6 35B A3B
14.1
OTIS Mock AIME 2024-2025
Qwen3.6 35B A3B leads by +17.8
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 4.1
68.9
Qwen3.6 35B A3B
86.7
Terminal Bench
Claude Opus 4.1 leads by +15.0
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence.
Claude Opus 4.1
38.0
Qwen3.6 35B A3B
23.0
WeirdML
Claude Opus 4.1 leads by +11.4
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Opus 4.1
45.9
Qwen3.6 35B A3B
34.5
Full benchmark table
| Benchmark | Claude Opus 4.1 | Qwen3.6 35B A3B |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 2.1 | 22.1 |
Dtbench | 66.7 | 56.5 |
FrontierMath-Tiers-1-3-v2-Private | 12.6 | 20.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 69.7 | 79.8 |
Lmca | 43.6 | 34.9 |
Mystery Game Puzzles | 13.0 | 14.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 68.9 | 86.7 |
Terminal Bench Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence. | 38.0 | 23.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 45.9 | 34.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $15.00 | $75.00 | 200K tokens (~100 books) | $300.00 | |
| $0.15 | $1.00 | 262K tokens (~131 books) | $3.63 |