token.app › Compare › Claude Haiku 4.5 vs DeepSeek V3.2
Claude Haiku 4.5 vs DeepSeek V3.2
Claude Haiku 4.5 leads on 1 of 2 shared benchmarks. DeepSeek V3.2 is 6.9× cheaper per token on a blended 3:1 basis. Claude Haiku 4.5 accepts the larger context window (200K).
Head to head
Blended price uses a 3:1 input:output mix
| Claude Haiku 4.5 | DeepSeek V3.2 | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Input $/1M | $1.00 | $0.260 |
| Output $/1M | $5.00 | $0.380 |
| Blended $/1M | $2.00 | $0.290 |
| Context window | 200K | 164K |
| Max output | 64K | 164K |
| Released | Oct 2025 | Dec 2025 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 71.2% | 71.2% |
| OTIS Mock AIME | 66.7% | 48.9% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Claude Haiku 4.5 if…
- Higher OTIS Mock AIME (66.7% vs 48.9%)
- Larger context window (200K)
Choose DeepSeek V3.2 if…
- Costs less per token — $0.290 vs $2.00 blended
- Open weights — self-hostable
- Newer model (released Dec 2025)
FAQ
Which is better, Claude Haiku 4.5 or DeepSeek V3.2?
Across the 2 benchmarks both models have independently-run scores for, Claude Haiku 4.5 leads on 1 and DeepSeek V3.2 leads on 0. Benchmarks are one input — price and context window are on this page too.
Is Claude Haiku 4.5 cheaper than DeepSeek V3.2?
DeepSeek V3.2 is cheaper: $0.290 versus $2.00 per million tokens blended at 3:1 input:output. Input alone: $1.00 vs $0.260. Output alone: $5.00 vs $0.380.
What context windows do Claude Haiku 4.5 and DeepSeek V3.2 have?
Claude Haiku 4.5: 200,000 tokens. DeepSeek V3.2: 163,840 tokens.
Who makes Claude Haiku 4.5 and DeepSeek V3.2?
Claude Haiku 4.5 is made by Anthropic. DeepSeek V3.2 is made by DeepSeek.
Related comparisons