Compare · ModelsLive · 2 picked · head to head
DeepSeek V3.1 vs o1
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
o1 wins on 3/4 benchmarks
o1 wins 3 of 4 shared benchmarks. Leads in knowledge · reasoning · coding.
Category leads
knowledge·o1reasoning·o1coding·o1
Hype vs Reality
Attention vs performance
DeepSeek V3.1
#88 by perf·no signal
o1
#59 by perf·no signal
Best value
DeepSeek V3.1
75.5x better value than o1
DeepSeek V3.1
113.6 pts/$
$0.45/M
o1
1.5 pts/$
$37.50/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
4 benchmarks · 2 models
DeepSeek V3.1o1
Fiction.LiveBench
o1 leads by +30.5
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
DeepSeek V3.1
52.8
o1
83.3
Lech Mazur Writing
DeepSeek V3.1 leads by +15.0
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
DeepSeek V3.1
85.2
o1
70.2
SimpleBench
o1 leads by +0.1
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
DeepSeek V3.1
28.0
o1
28.1
WeirdML
o1 leads by +5.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V3.1
38.4
o1
43.8
Full benchmark table
| Benchmark | DeepSeek V3.1 | o1 |
|---|---|---|
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 52.8 | 83.3 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 85.2 | 70.2 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 28.0 | 28.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 38.4 | 43.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.15 | $0.75 | 33K tokens (~16 books) | $3.00 | |
| $15.00 | $60.00 | 200K tokens (~100 books) | $262.50 |
People also compared