Compare · ModelsLive · 2 picked · head to head
Claude Opus 4.5 vs Qwen3.6 Max Preview
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3.6 Max Preview wins on 8/13 benchmarks
Qwen3.6 Max Preview wins 8 of 13 shared benchmarks. Leads in arena · knowledge · math.
Category leads
arena·Qwen3.6 Max Previewknowledge·Qwen3.6 Max Previewgeneral·Claude Opus 4.5math·Qwen3.6 Max Previewreasoning·Qwen3.6 Max Previewcoding·Claude Opus 4.5
Hype vs Reality
Attention vs performance
Claude Opus 4.5
#185 by perf·#7 by attention
Qwen3.6 Max Preview
#119 by perf·#2 by attention
Best value
Qwen3.6 Max Preview
5.1x better value than Claude Opus 4.5
Claude Opus 4.5
2.8 pts/$
$15.00/M
Qwen3.6 Max Preview
14.2 pts/$
$3.59/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
13 benchmarks · 2 models
Claude Opus 4.5Qwen3.6 Max Preview
Chatbot Arena Elo · Coding
Qwen3.6 Max Preview leads by +13.1
Claude Opus 4.5
1468.5
Qwen3.6 Max Preview
1481.5
Chatbot Arena Elo · Overall
Claude Opus 4.5 leads by +9.5
Claude Opus 4.5
1469.8
Qwen3.6 Max Preview
1460.3
Chess Puzzles
Qwen3.6 Max Preview leads by +6.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Opus 4.5
9.5
Qwen3.6 Max Preview
15.8
Dtbench
Claude Opus 4.5 leads by +4.5
Claude Opus 4.5
83.1
Qwen3.6 Max Preview
78.7
FrontierMath-2025-02-28-Private
Qwen3.6 Max Preview leads by +19.8
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude Opus 4.5
20.7
Qwen3.6 Max Preview
40.5
FrontierMath-Tier-4-2025-07-01-Private
Qwen3.6 Max Preview leads by +2.8
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
Claude Opus 4.5
4.2
Qwen3.6 Max Preview
6.9
GPQA diamond
Qwen3.6 Max Preview leads by +1.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 4.5
81.4
Qwen3.6 Max Preview
83.2
Lmca
Claude Opus 4.5 leads by +2.3
Claude Opus 4.5
52.3
Qwen3.6 Max Preview
50.0
Mystery Game Puzzles
Claude Opus 4.5 leads by +3.3
Claude Opus 4.5
14.1
Qwen3.6 Max Preview
10.8
OTIS Mock AIME 2024-2025
Qwen3.6 Max Preview leads by +5.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 4.5
86.1
Qwen3.6 Max Preview
91.1
SimpleBench
Qwen3.6 Max Preview leads by +1.2
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Opus 4.5
54.4
Qwen3.6 Max Preview
55.6
SimpleQA Verified
Qwen3.6 Max Preview leads by +10.2
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Opus 4.5
41.8
Qwen3.6 Max Preview
52.0
SWE-Bench verified
SWE-bench Verified · 500 human-validated tasks from 12 real Python repositories (Django, Flask, scikit-learn, sympy, and others). Each task requires the model to produce a git patch that resolves a real GitHub issue and passes the test suite. The verified subset eliminates ambiguous tasks from the original SWE-bench. Claude Mythos Preview leads at 93.9%, crossing 90% for the first time in 2026. Opus 4.6 scores 80.8%. The benchmark remains the most-cited evaluation for code-generation capability.
Claude Opus 4.5
76.7
Qwen3.6 Max Preview
76.7
Full benchmark table
| Benchmark | Claude Opus 4.5 | Qwen3.6 Max Preview |
|---|---|---|
Chatbot Arena Elo · Coding | 1468.5 | 1481.5 |
Chatbot Arena Elo · Overall | 1469.8 | 1460.3 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 9.5 | 15.8 |
Dtbench | 83.1 | 78.7 |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 20.7 | 40.5 |
FrontierMath-Tier-4-2025-07-01-Private FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning. | 4.2 | 6.9 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 81.4 | 83.2 |
Lmca | 52.3 | 50.0 |
Mystery Game Puzzles | 14.1 | 10.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 86.1 | 91.1 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 54.4 | 55.6 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 41.8 | 52.0 |
SWE-Bench verified SWE-bench Verified · 500 human-validated tasks from 12 real Python repositories (Django, Flask, scikit-learn, sympy, and others). Each task requires the model to produce a git patch that resolves a real GitHub issue and passes the test suite. The verified subset eliminates ambiguous tasks from the original SWE-bench. Claude Mythos Preview leads at 93.9%, crossing 90% for the first time in 2026. Opus 4.6 scores 80.8%. The benchmark remains the most-cited evaluation for code-generation capability. | 76.7 | 76.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $5.00 | $25.00 | 200K tokens (~100 books) | $100.00 | |
| $1.03 | $6.16 | 262K tokens (~131 books) | $23.11 |
People also compared