Head-to-head · multimodal vs multimodal

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

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

ByteDance

Doubao 1.5 Pro Turbo

Doubao 1.5 Pro Turbo is a multimodal model from ByteDance. It offers a 128,000-token context window, costs $13.81 per million input tokens and $71.10 per million output tokens, and averages 79.4 across the index's benchmark suite.

Input
$13.81 / 1M
Output
$71.10 / 1M
Context
128,000
Avg score
79.4
Open weights
No
Full Doubao 1.5 Pro Turbo page
Baidu

ERNIE 4.5

ERNIE 4.5 is a multimodal model from Baidu. It offers a 65,536-token context window, costs $13.44 per million input tokens and $56.59 per million output tokens, and averages 80.0 across the index's benchmark suite.

Input
$13.44 / 1M
Output
$56.59 / 1M
Context
65,536
Avg score
80.0
Open weights
No
Full ERNIE 4.5 page

Specification comparison

SpecDoubao 1.5 Pro TurboERNIE 4.5Edge
Input price / 1M$13.81$13.44B
Output price / 1M$71.10$56.59B
Context window128,00065,536A
Max output65,53632,768A
Average score79.480.0B
Arena Elo1433.01414.8A
Open weightsNoNoTie

Benchmark comparison

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

BenchmarkDoubao 1.5 Pro TurboERNIE 4.5GapWinner
MMLU-Pro80.383.73.4ERNIE 4.5
GPQA Diamond75.477.21.8ERNIE 4.5
SWE-bench Verified67.768.20.5ERNIE 4.5
HumanEval85.083.91.1Doubao 1.5 Pro Turbo
MATH-50081.481.30.1Doubao 1.5 Pro Turbo
AIME 202575.675.90.3ERNIE 4.5
LiveCodeBench72.372.90.6ERNIE 4.5
IFEval88.986.42.5Doubao 1.5 Pro Turbo
TruthfulQA80.983.02.1ERNIE 4.5
HellaSwag88.289.21.0ERNIE 4.5
MMMU77.678.00.4ERNIE 4.5
Arena Elo1433.01414.818.2Doubao 1.5 Pro Turbo

Price analysis

On a blended 3:1 input-to-output basis, Doubao 1.5 Pro Turbo costs about $28.13 per million tokens and ERNIE 4.5 costs about $24.23. ERNIE 4.5 is roughly 14% cheaper than Doubao 1.5 Pro Turbo. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.

Doubao 1.5 Pro Turbo has the larger context window at 128,000 tokens, compared with 65,536 for ERNIE 4.5. That matters for long documents, large codebases and multi-step agent traces.

Verdict

Across 12 shared benchmarks, Doubao 1.5 Pro Turbo wins 4, ERNIE 4.5 wins 8, and 0 are tied. On the index average, ERNIE 4.5 leads Doubao 1.5 Pro Turbo by 0.6 points (80.0 versus 79.4).

The price picture favours ERNIE 4.5. The context picture favours Doubao 1.5 Pro 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 ERNIE 4.5 for quality-sensitive work, and check whether its price holds at your expected volume before committing.

Choose Doubao 1.5 Pro Turbo if

  • You need the larger 128,000-token context window.
  • You need the larger 65,536-token output limit.

Choose ERNIE 4.5 if

  • You want the higher average benchmark score in this index.
  • Unit cost matters and you want the cheaper blended price.

FAQ

Is Doubao 1.5 Pro Turbo better than ERNIE 4.5?

On the index average, ERNIE 4.5 leads Doubao 1.5 Pro Turbo by 0.6 points (80.0 versus 79.4). The better choice depends on price, context and your task. Doubao 1.5 Pro Turbo wins 4 benchmarks, ERNIE 4.5 wins 8.

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

ERNIE 4.5 is cheaper on a blended 3:1 basis at about $24.23 per million tokens, versus $28.13 for Doubao 1.5 Pro Turbo.

Which has the larger context window?

Doubao 1.5 Pro Turbo has the larger context window at 128,000 tokens. ERNIE 4.5 has 65,536 tokens.

Are these models open weights?

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

Which should I choose for production?

If you need a single default, start with ERNIE 4.5 for quality-sensitive work, and check whether its price holds at your expected volume before committing.

Related comparisons