Compare · ModelsLive · 2 picked · head to head
o1 vs Qwen3 235B A22B Thinking 2507
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
o1 wins on 3/6 benchmarks
o1 wins 3 of 6 shared benchmarks. Leads in math · coding.
Category leads
knowledge·Qwen3 235B A22B Thinking 2507math·o1coding·o1
Hype vs Reality
Attention vs performance
o1
#59 by perf·no signal
Qwen3 235B A22B Thinking 2507
#66 by perf·no signal
Best value
Qwen3 235B A22B Thinking 2507
45.2x better value than o1
o1
1.5 pts/$
$37.50/M
Qwen3 235B A22B Thinking 2507
68.0 pts/$
$0.82/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
6 benchmarks · 2 models
o1Qwen3 235B A22B Thinking 2507
Fiction.LiveBench
o1 leads by +8.3
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
o1
83.3
Qwen3 235B A22B Thinking 2507
75.0
FrontierMath-2025-02-28-Private
o1 leads by +0.8
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
o1
9.3
Qwen3 235B A22B Thinking 2507
8.5
GPQA diamond
Qwen3 235B A22B Thinking 2507 leads by +4.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
o1
69.0
Qwen3 235B A22B Thinking 2507
73.4
Lech Mazur Writing
Qwen3 235B A22B Thinking 2507 leads by +14.8
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
o1
70.2
Qwen3 235B A22B Thinking 2507
85.0
OTIS Mock AIME 2024-2025
Qwen3 235B A22B Thinking 2507 leads by +13.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
o1
73.3
Qwen3 235B A22B Thinking 2507
86.7
WeirdML
o1 leads by +2.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
o1
43.8
Qwen3 235B A22B Thinking 2507
41.0
Full benchmark table
| Benchmark | o1 | Qwen3 235B A22B Thinking 2507 |
|---|---|---|
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 83.3 | 75.0 |
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. | 9.3 | 8.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 69.0 | 73.4 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 70.2 | 85.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 73.3 | 86.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 43.8 | 41.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $15.00 | $60.00 | 200K tokens (~100 books) | $262.50 | |
| $0.15 | $1.50 | 131K tokens (~66 books) | $4.86 |