Head-to-head · multimodal vs multimodal

Command A Pro vs ERNIE 4.5 Max: which model should you choose?

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

Cohere

Command A Pro

Command A Pro is a multimodal model from Cohere. It offers a 200,000-token context window, costs $14.28 per million input tokens and $68.05 per million output tokens, and averages 81.3 across the index's benchmark suite.

Input
$14.28 / 1M
Output
$68.05 / 1M
Context
200,000
Avg score
81.3
Open weights
No
Full Command A Pro page
Baidu

ERNIE 4.5 Max

ERNIE 4.5 Max is a multimodal model from Baidu. It offers a 128,000-token context window, costs $14.41 per million input tokens and $53.71 per million output tokens, and averages 80.6 across the index's benchmark suite.

Input
$14.41 / 1M
Output
$53.71 / 1M
Context
128,000
Avg score
80.6
Open weights
No
Full ERNIE 4.5 Max page

Specification comparison

SpecCommand A ProERNIE 4.5 MaxEdge
Input price / 1M$14.28$14.41A
Output price / 1M$68.05$53.71B
Context window200,000128,000A
Max output16,38465,536B
Average score81.380.6A
Arena Elo1434.61423.7A
Open weightsNoNoTie

Benchmark comparison

Command A Pro wins 7, ERNIE 4.5 Max wins 5, and 0 benchmarks are tied. The table shows the modelled score for each model and the gap.

BenchmarkCommand A ProERNIE 4.5 MaxGapWinner
MMLU-Pro81.380.80.5Command A Pro
GPQA Diamond79.176.42.7Command A Pro
SWE-bench Verified71.268.92.3Command A Pro
HumanEval87.587.70.2ERNIE 4.5 Max
MATH-50083.184.21.1ERNIE 4.5 Max
AIME 202578.279.51.3ERNIE 4.5 Max
LiveCodeBench74.073.01.0Command A Pro
IFEval89.087.11.9Command A Pro
TruthfulQA83.383.60.3ERNIE 4.5 Max
HellaSwag90.187.72.4Command A Pro
MMMU77.278.10.9ERNIE 4.5 Max
Arena Elo1434.61423.710.9Command A Pro

Price analysis

On a blended 3:1 input-to-output basis, Command A Pro costs about $27.72 per million tokens and ERNIE 4.5 Max costs about $24.23. ERNIE 4.5 Max is roughly 13% cheaper than Command A Pro. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.

Command A Pro has the larger context window at 200,000 tokens, compared with 128,000 for ERNIE 4.5 Max. That matters for long documents, large codebases and multi-step agent traces.

Verdict

Across 12 shared benchmarks, Command A Pro wins 7, ERNIE 4.5 Max wins 5, and 0 are tied. On the index average, Command A Pro leads ERNIE 4.5 Max by 0.7 points (81.3 versus 80.6).

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

Choose Command A Pro if

  • You want the higher average benchmark score in this index.
  • You need the larger 200,000-token context window.

Choose ERNIE 4.5 Max if

  • Unit cost matters and you want the cheaper blended price.
  • You need the larger 65,536-token output limit.

FAQ

Is Command A Pro better than ERNIE 4.5 Max?

On the index average, Command A Pro leads ERNIE 4.5 Max by 0.7 points (81.3 versus 80.6). The better choice depends on price, context and your task. Command A Pro wins 7 benchmarks, ERNIE 4.5 Max wins 5.

Which is cheaper, Command A Pro or ERNIE 4.5 Max?

ERNIE 4.5 Max is cheaper on a blended 3:1 basis at about $24.23 per million tokens, versus $27.72 for Command A Pro.

Which has the larger context window?

Command A Pro has the larger context window at 200,000 tokens. ERNIE 4.5 Max has 128,000 tokens.

Are these models open weights?

Command A Pro is proprietary; ERNIE 4.5 Max is proprietary.

Which should I choose for production?

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

Related comparisons