Compare · ModelsLive · 2 picked · head to head
DeepSeek V3.1 vs DeepSeek V3.2 Exp
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V3.2 Exp wins on 5/5 benchmarks
DeepSeek V3.2 Exp wins 5 of 5 shared benchmarks. Leads in arena · general · knowledge.
Category leads
arena·DeepSeek V3.2 Expgeneral·DeepSeek V3.2 Expknowledge·DeepSeek V3.2 Expcoding·DeepSeek V3.2 Exp
Hype vs Reality
Attention vs performance
DeepSeek V3.1
#118 by perf·no signal
DeepSeek V3.2 Exp
#133 by perf·no signal
Best value
DeepSeek V3.2 Exp
1.7x better value than DeepSeek V3.1
DeepSeek V3.1
84.5 pts/$
$0.60/M
DeepSeek V3.2 Exp
142.4 pts/$
$0.34/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
DeepSeek
$3.4B·Tier 1
Head to head
5 benchmarks · 2 models
DeepSeek V3.1DeepSeek V3.2 Exp
Chatbot Arena Elo · Overall
DeepSeek V3.2 Exp leads by +4.9
DeepSeek V3.1
1417.2
DeepSeek V3.2 Exp
1422.1
Dtbench
DeepSeek V3.2 Exp leads by +8.4
DeepSeek V3.1
71.1
DeepSeek V3.2 Exp
79.5
Fiction.LiveBench
DeepSeek V3.2 Exp 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
DeepSeek V3.2 Exp
83.3
Lmca
DeepSeek V3.2 Exp leads by +5.7
DeepSeek V3.1
28.6
DeepSeek V3.2 Exp
34.3
WeirdML
DeepSeek V3.2 Exp leads by +1.1
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V3.1
38.4
DeepSeek V3.2 Exp
39.5
Full benchmark table
| Benchmark | DeepSeek V3.1 | DeepSeek V3.2 Exp |
|---|---|---|
Chatbot Arena Elo · Overall | 1417.2 | 1422.1 |
Dtbench | 71.1 | 79.5 |
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 |
Lmca | 28.6 | 34.3 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 38.4 | 39.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.25 | $0.95 | 164K tokens (~82 books) | $4.25 | |
| $0.27 | $0.41 | 164K tokens (~82 books) | $3.05 |
People also compared