Claude Haiku 4.5 Turbo vs Doubao 1.5 Pro Reasoning: which model should you choose?
We compared Claude Haiku 4.5 Turbo and Doubao 1.5 Pro Reasoning on price, context window and 12 benchmarks. Doubao 1.5 Pro Reasoning has the stronger average benchmark score; Claude Haiku 4.5 Turbo is cheaper on a blended 3:1 basis.
Claude Haiku 4.5 Turbo
Claude Haiku 4.5 Turbo is a multimodal model from Anthropic. It offers a 200,000-token context window, costs $14.37 per million input tokens and $54.76 per million output tokens, and averages 80.0 across the index's benchmark suite.
- Input
- $14.37 / 1M
- Output
- $54.76 / 1M
- Context
- 200,000
- Avg score
- 80.0
- Open weights
- No
Doubao 1.5 Pro Reasoning
Doubao 1.5 Pro Reasoning is a multimodal model from ByteDance. It offers a 128,000-token context window, costs $14.56 per million input tokens and $58.10 per million output tokens, and averages 81.6 across the index's benchmark suite.
- Input
- $14.56 / 1M
- Output
- $58.10 / 1M
- Context
- 128,000
- Avg score
- 81.6
- Open weights
- No
Specification comparison
| Spec | Claude Haiku 4.5 Turbo | Doubao 1.5 Pro Reasoning | Edge |
|---|---|---|---|
| Input price / 1M | $14.37 | $14.56 | A |
| Output price / 1M | $54.76 | $58.10 | A |
| Context window | 200,000 | 128,000 | A |
| Max output | 32,768 | 16,384 | A |
| Average score | 80.0 | 81.6 | B |
| Arena Elo | 1434.5 | 1439.2 | B |
| Open weights | No | No | Tie |
Benchmark comparison
Claude Haiku 4.5 Turbo wins 0, Doubao 1.5 Pro Reasoning wins 12, and 0 benchmarks are tied. The table shows the modelled score for each model and the gap.
| Benchmark | Claude Haiku 4.5 Turbo | Doubao 1.5 Pro Reasoning | Gap | Winner |
|---|---|---|---|---|
| MMLU-Pro | 80.6 | 81.8 | 1.2 | Doubao 1.5 Pro Reasoning |
| GPQA Diamond | 75.1 | 78.1 | 3.0 | Doubao 1.5 Pro Reasoning |
| SWE-bench Verified | 68.4 | 69.7 | 1.3 | Doubao 1.5 Pro Reasoning |
| HumanEval | 87.0 | 87.4 | 0.4 | Doubao 1.5 Pro Reasoning |
| MATH-500 | 83.7 | 85.1 | 1.4 | Doubao 1.5 Pro Reasoning |
| AIME 2025 | 79.2 | 81.4 | 2.2 | Doubao 1.5 Pro Reasoning |
| LiveCodeBench | 71.7 | 73.9 | 2.2 | Doubao 1.5 Pro Reasoning |
| IFEval | 87.1 | 88.7 | 1.6 | Doubao 1.5 Pro Reasoning |
| TruthfulQA | 81.0 | 82.3 | 1.3 | Doubao 1.5 Pro Reasoning |
| HellaSwag | 88.1 | 90.7 | 2.6 | Doubao 1.5 Pro Reasoning |
| MMMU | 77.7 | 78.1 | 0.4 | Doubao 1.5 Pro Reasoning |
| Arena Elo | 1434.5 | 1439.2 | 4.7 | Doubao 1.5 Pro Reasoning |
Price analysis
On a blended 3:1 input-to-output basis, Claude Haiku 4.5 Turbo costs about $24.47 per million tokens and Doubao 1.5 Pro Reasoning costs about $25.45. Claude Haiku 4.5 Turbo is roughly 4% cheaper than Doubao 1.5 Pro Reasoning. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.
Claude Haiku 4.5 Turbo has the larger context window at 200,000 tokens, compared with 128,000 for Doubao 1.5 Pro Reasoning. That matters for long documents, large codebases and multi-step agent traces.
Verdict
Across 12 shared benchmarks, Claude Haiku 4.5 Turbo wins 0, Doubao 1.5 Pro Reasoning wins 12, and 0 are tied. On the index average, Doubao 1.5 Pro Reasoning leads Claude Haiku 4.5 Turbo by 1.6 points (81.6 versus 80.0).
The price picture favours Claude Haiku 4.5 Turbo. The context picture favours Claude Haiku 4.5 Turbo. Those two dimensions often matter more than a few benchmark points once a model is good enough for the task.
If you need a single default, start with Doubao 1.5 Pro Reasoning for quality-sensitive work and Claude Haiku 4.5 Turbo for high-volume, well-scoped tasks. Run both on a sample of your own traffic before locking in a choice.
Choose Claude Haiku 4.5 Turbo if
- Unit cost matters and you want the cheaper blended price.
- You need the larger 200,000-token context window.
- You need the larger 32,768-token output limit.
Choose Doubao 1.5 Pro Reasoning if
- You want the higher average benchmark score in this index.
- The workload needs multi-step reasoning.
FAQ
Is Claude Haiku 4.5 Turbo better than Doubao 1.5 Pro Reasoning?
On the index average, Doubao 1.5 Pro Reasoning leads Claude Haiku 4.5 Turbo by 1.6 points (81.6 versus 80.0). The better choice depends on price, context and your task. Claude Haiku 4.5 Turbo wins 0 benchmarks, Doubao 1.5 Pro Reasoning wins 12.
Which is cheaper, Claude Haiku 4.5 Turbo or Doubao 1.5 Pro Reasoning?
Claude Haiku 4.5 Turbo is cheaper on a blended 3:1 basis at about $24.47 per million tokens, versus $25.45 for Doubao 1.5 Pro Reasoning.
Which has the larger context window?
Claude Haiku 4.5 Turbo has the larger context window at 200,000 tokens. Doubao 1.5 Pro Reasoning has 128,000 tokens.
Are these models open weights?
Claude Haiku 4.5 Turbo is proprietary; Doubao 1.5 Pro Reasoning is proprietary.
Which should I choose for production?
If you need a single default, start with Doubao 1.5 Pro Reasoning for quality-sensitive work and Claude Haiku 4.5 Turbo for high-volume, well-scoped tasks. Run both on a sample of your own traffic before locking in a choice.