Head-to-head · multimodal vs multimodal

Doubao 1.5 Pro vs ERNIE 4.5 Pro: which model should you choose?

We compared Doubao 1.5 Pro and ERNIE 4.5 Pro on price, context window and 12 benchmarks. ERNIE 4.5 Pro has the stronger average benchmark score; Doubao 1.5 Pro is cheaper on a blended 3:1 basis.

ByteDance

Doubao 1.5 Pro

Doubao 1.5 Pro is a multimodal model from ByteDance. It offers a 200,000-token context window, costs $13.65 per million input tokens and $48.98 per million output tokens, and averages 79.7 across the index's benchmark suite.

Input
$13.65 / 1M
Output
$48.98 / 1M
Context
200,000
Avg score
79.7
Open weights
No
Full Doubao 1.5 Pro page
Baidu

ERNIE 4.5 Pro

ERNIE 4.5 Pro is a multimodal model from Baidu. It offers a 1,000,000-token context window, costs $13.89 per million input tokens and $65.19 per million output tokens, and averages 80.5 across the index's benchmark suite.

Input
$13.89 / 1M
Output
$65.19 / 1M
Context
1,000,000
Avg score
80.5
Open weights
No
Full ERNIE 4.5 Pro page

Specification comparison

SpecDoubao 1.5 ProERNIE 4.5 ProEdge
Input price / 1M$13.65$13.89A
Output price / 1M$48.98$65.19A
Context window200,0001,000,000B
Max output128,00032,768A
Average score79.780.5B
Arena Elo1428.31414.3A
Open weightsNoNoTie

Benchmark comparison

Doubao 1.5 Pro wins 4, ERNIE 4.5 Pro wins 8, and 0 benchmarks are tied. The table shows the modelled score for each model and the gap.

BenchmarkDoubao 1.5 ProERNIE 4.5 ProGapWinner
MMLU-Pro82.880.32.5Doubao 1.5 Pro
GPQA Diamond73.174.71.6ERNIE 4.5 Pro
SWE-bench Verified70.466.53.9Doubao 1.5 Pro
HumanEval82.686.94.3ERNIE 4.5 Pro
MATH-50084.487.22.8ERNIE 4.5 Pro
AIME 202575.276.31.1ERNIE 4.5 Pro
LiveCodeBench73.776.42.7ERNIE 4.5 Pro
IFEval85.586.00.5ERNIE 4.5 Pro
TruthfulQA81.683.11.5ERNIE 4.5 Pro
HellaSwag88.990.21.3ERNIE 4.5 Pro
MMMU79.078.40.6Doubao 1.5 Pro
Arena Elo1428.31414.314.0Doubao 1.5 Pro

Price analysis

On a blended 3:1 input-to-output basis, Doubao 1.5 Pro costs about $22.48 per million tokens and ERNIE 4.5 Pro costs about $26.71. Doubao 1.5 Pro is roughly 16% cheaper than ERNIE 4.5 Pro. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.

ERNIE 4.5 Pro has the larger context window at 1,000,000 tokens, compared with 200,000 for Doubao 1.5 Pro. That matters for long documents, large codebases and multi-step agent traces.

Verdict

Across 12 shared benchmarks, Doubao 1.5 Pro wins 4, ERNIE 4.5 Pro wins 8, and 0 are tied. On the index average, ERNIE 4.5 Pro leads Doubao 1.5 Pro by 0.8 points (80.5 versus 79.7).

The price picture favours Doubao 1.5 Pro. The context picture favours ERNIE 4.5 Pro. 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 ERNIE 4.5 Pro for quality-sensitive work and Doubao 1.5 Pro for high-volume, well-scoped tasks. Run both on a sample of your own traffic before locking in a choice.

Choose Doubao 1.5 Pro if

  • Unit cost matters and you want the cheaper blended price.
  • You need the larger 128,000-token output limit.

Choose ERNIE 4.5 Pro if

  • You want the higher average benchmark score in this index.
  • You need the larger 1,000,000-token context window.

FAQ

Is Doubao 1.5 Pro better than ERNIE 4.5 Pro?

On the index average, ERNIE 4.5 Pro leads Doubao 1.5 Pro by 0.8 points (80.5 versus 79.7). The better choice depends on price, context and your task. Doubao 1.5 Pro wins 4 benchmarks, ERNIE 4.5 Pro wins 8.

Which is cheaper, Doubao 1.5 Pro or ERNIE 4.5 Pro?

Doubao 1.5 Pro is cheaper on a blended 3:1 basis at about $22.48 per million tokens, versus $26.71 for ERNIE 4.5 Pro.

Which has the larger context window?

ERNIE 4.5 Pro has the larger context window at 1,000,000 tokens. Doubao 1.5 Pro has 200,000 tokens.

Are these models open weights?

Doubao 1.5 Pro is proprietary; ERNIE 4.5 Pro is proprietary.

Which should I choose for production?

If you need a single default, start with ERNIE 4.5 Pro for quality-sensitive work and Doubao 1.5 Pro for high-volume, well-scoped tasks. Run both on a sample of your own traffic before locking in a choice.

Related comparisons