Head-to-head · multimodal vs multimodal

ERNIE 4.5 Turbo vs Reka Core Pro: which model should you choose?

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

Baidu

ERNIE 4.5 Turbo

ERNIE 4.5 Turbo is a multimodal model from Baidu. It offers a 128,000-token context window, costs $13.75 per million input tokens and $54.36 per million output tokens, and averages 79.7 across the index's benchmark suite.

Input
$13.75 / 1M
Output
$54.36 / 1M
Context
128,000
Avg score
79.7
Open weights
No
Full ERNIE 4.5 Turbo page
Reka AI

Reka Core Pro

Reka Core Pro is a multimodal model from Reka AI. It offers a 65,536-token context window, costs $13.44 per million input tokens and $69.38 per million output tokens, and averages 79.9 across the index's benchmark suite.

Input
$13.44 / 1M
Output
$69.38 / 1M
Context
65,536
Avg score
79.9
Open weights
No
Full Reka Core Pro page

Specification comparison

SpecERNIE 4.5 TurboReka Core ProEdge
Input price / 1M$13.75$13.44B
Output price / 1M$54.36$69.38A
Context window128,00065,536A
Max output32,76865,536B
Average score79.779.9B
Arena Elo1419.81421.1B
Open weightsNoNoTie

Benchmark comparison

ERNIE 4.5 Turbo wins 5, Reka Core Pro wins 7, and 0 benchmarks are tied. The table shows the modelled score for each model and the gap.

BenchmarkERNIE 4.5 TurboReka Core ProGapWinner
MMLU-Pro84.083.20.8ERNIE 4.5 Turbo
GPQA Diamond73.078.05.0Reka Core Pro
SWE-bench Verified67.566.80.7ERNIE 4.5 Turbo
HumanEval86.483.43.0ERNIE 4.5 Turbo
MATH-50086.485.90.5ERNIE 4.5 Turbo
AIME 202580.775.84.9ERNIE 4.5 Turbo
LiveCodeBench70.571.81.3Reka Core Pro
IFEval85.286.00.8Reka Core Pro
TruthfulQA82.583.40.9Reka Core Pro
HellaSwag87.088.71.7Reka Core Pro
MMMU73.776.42.7Reka Core Pro
Arena Elo1419.81421.11.3Reka Core Pro

Price analysis

On a blended 3:1 input-to-output basis, ERNIE 4.5 Turbo costs about $23.90 per million tokens and Reka Core Pro costs about $27.42. ERNIE 4.5 Turbo is roughly 13% cheaper than Reka Core Pro. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.

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

Verdict

Across 12 shared benchmarks, ERNIE 4.5 Turbo wins 5, Reka Core Pro wins 7, and 0 are tied. On the index average, Reka Core Pro leads ERNIE 4.5 Turbo by 0.2 points (79.9 versus 79.7).

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

Choose ERNIE 4.5 Turbo if

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

Choose Reka Core Pro if

  • You want the higher average benchmark score in this index.
  • You need the larger 65,536-token output limit.

FAQ

Is ERNIE 4.5 Turbo better than Reka Core Pro?

On the index average, Reka Core Pro leads ERNIE 4.5 Turbo by 0.2 points (79.9 versus 79.7). The better choice depends on price, context and your task. ERNIE 4.5 Turbo wins 5 benchmarks, Reka Core Pro wins 7.

Which is cheaper, ERNIE 4.5 Turbo or Reka Core Pro?

ERNIE 4.5 Turbo is cheaper on a blended 3:1 basis at about $23.90 per million tokens, versus $27.42 for Reka Core Pro.

Which has the larger context window?

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

Are these models open weights?

ERNIE 4.5 Turbo is proprietary; Reka Core Pro is proprietary.

Which should I choose for production?

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

Related comparisons