Doubao 1.5 Pro Reasoning vs ERNIE 4.5 Reasoning: which model should you choose?
We compared Doubao 1.5 Pro Reasoning and ERNIE 4.5 Reasoning on price, context window and 12 benchmarks. Doubao 1.5 Pro Reasoning has the stronger average benchmark score; Doubao 1.5 Pro Reasoning is cheaper on a blended 3:1 basis.
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
ERNIE 4.5 Reasoning
ERNIE 4.5 Reasoning is a multimodal model from Baidu. It offers a 1,000,000-token context window, costs $14.36 per million input tokens and $78.75 per million output tokens, and averages 79.8 across the index's benchmark suite.
- Input
- $14.36 / 1M
- Output
- $78.75 / 1M
- Context
- 1,000,000
- Avg score
- 79.8
- Open weights
- No
Specification comparison
| Spec | Doubao 1.5 Pro Reasoning | ERNIE 4.5 Reasoning | Edge |
|---|---|---|---|
| Input price / 1M | $14.56 | $14.36 | B |
| Output price / 1M | $58.10 | $78.75 | A |
| Context window | 128,000 | 1,000,000 | B |
| Max output | 16,384 | 8,192 | A |
| Average score | 81.6 | 79.8 | A |
| Arena Elo | 1439.2 | 1421.5 | A |
| Open weights | No | No | Tie |
Benchmark comparison
Doubao 1.5 Pro Reasoning wins 9, ERNIE 4.5 Reasoning wins 2, and 1 benchmarks are tied. The table shows the modelled score for each model and the gap.
| Benchmark | Doubao 1.5 Pro Reasoning | ERNIE 4.5 Reasoning | Gap | Winner |
|---|---|---|---|---|
| MMLU-Pro | 81.8 | 80.6 | 1.2 | Doubao 1.5 Pro Reasoning |
| GPQA Diamond | 78.1 | 75.7 | 2.4 | Doubao 1.5 Pro Reasoning |
| SWE-bench Verified | 69.7 | 69.8 | 0.1 | ERNIE 4.5 Reasoning |
| HumanEval | 87.4 | 85.0 | 2.4 | Doubao 1.5 Pro Reasoning |
| MATH-500 | 85.1 | 82.5 | 2.6 | Doubao 1.5 Pro Reasoning |
| AIME 2025 | 81.4 | 78.1 | 3.3 | Doubao 1.5 Pro Reasoning |
| LiveCodeBench | 73.9 | 71.9 | 2.0 | Doubao 1.5 Pro Reasoning |
| IFEval | 88.7 | 88.7 | 0.0 | Tie |
| TruthfulQA | 82.3 | 82.9 | 0.6 | ERNIE 4.5 Reasoning |
| HellaSwag | 90.7 | 88.0 | 2.7 | Doubao 1.5 Pro Reasoning |
| MMMU | 78.1 | 74.4 | 3.7 | Doubao 1.5 Pro Reasoning |
| Arena Elo | 1439.2 | 1421.5 | 17.7 | Doubao 1.5 Pro Reasoning |
Price analysis
On a blended 3:1 input-to-output basis, Doubao 1.5 Pro Reasoning costs about $25.45 per million tokens and ERNIE 4.5 Reasoning costs about $30.46. Doubao 1.5 Pro Reasoning is roughly 16% cheaper than ERNIE 4.5 Reasoning. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.
ERNIE 4.5 Reasoning has the larger context window at 1,000,000 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, Doubao 1.5 Pro Reasoning wins 9, ERNIE 4.5 Reasoning wins 2, and 1 are tied. On the index average, Doubao 1.5 Pro Reasoning leads ERNIE 4.5 Reasoning by 1.8 points (81.6 versus 79.8).
The price picture favours Doubao 1.5 Pro Reasoning. The context picture favours ERNIE 4.5 Reasoning. 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 check whether its price holds at your expected volume before committing.
Choose Doubao 1.5 Pro Reasoning if
- You want the higher average benchmark score in this index.
- Unit cost matters and you want the cheaper blended price.
- You need the larger 16,384-token output limit.
Choose ERNIE 4.5 Reasoning if
- You need the larger 1,000,000-token context window.
FAQ
Is Doubao 1.5 Pro Reasoning better than ERNIE 4.5 Reasoning?
On the index average, Doubao 1.5 Pro Reasoning leads ERNIE 4.5 Reasoning by 1.8 points (81.6 versus 79.8). The better choice depends on price, context and your task. Doubao 1.5 Pro Reasoning wins 9 benchmarks, ERNIE 4.5 Reasoning wins 2.
Which is cheaper, Doubao 1.5 Pro Reasoning or ERNIE 4.5 Reasoning?
Doubao 1.5 Pro Reasoning is cheaper on a blended 3:1 basis at about $25.45 per million tokens, versus $30.46 for ERNIE 4.5 Reasoning.
Which has the larger context window?
ERNIE 4.5 Reasoning has the larger context window at 1,000,000 tokens. Doubao 1.5 Pro Reasoning has 128,000 tokens.
Are these models open weights?
Doubao 1.5 Pro Reasoning is proprietary; ERNIE 4.5 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 check whether its price holds at your expected volume before committing.