Compare/ERNIE 5.0 Thinking Preview vs GPT-5.4 mini (xhigh)

ERNIE 5.0 Thinking PreviewvsGPT-5.4 mini (xhigh)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Baidu

ERNIE 5.0 Thinking Preview

Input
$0/M
Output
$0/M
Speed
TTFT
OpenAI

GPT-5.4 mini (xhigh)

Input
$0.75/M
Output
$4.5/M
Speed
219 tok/s
TTFT
3.82s

Winner by Category

Cheaper
ERNIE 5.0 Thinking Preview
Faster (tok/s)
GPT-5.4 mini (xhigh)
Lower Latency
ERNIE 5.0 Thinking Preview
Benchmarks (4-7)
GPT-5.4 mini (xhigh)

Pricing Comparison

MetricERNIE 5.0 Thinking PreviewGPT-5.4 mini (xhigh)
Input ($/M tokens)$0$0.75
Output ($/M tokens)$0$4.5
Cost for 1M input + 100K output tokens:
ERNIE 5.0 Thinking Preview$0.00
GPT-5.4 mini (xhigh)$1.20

Speed Comparison

Output Speed (tokens/s) — higher is better
ERNIE 5.0 Thinking Preview
GPT-5.4 mini (xhigh)
219 tok/s
Time to First Token (seconds) — lower is better
ERNIE 5.0 Thinking Preview
GPT-5.4 mini (xhigh)
3.82s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
29.148.1
Coding Index
29.251.5
Math Index
85.0
GPQA Diamond
77.7%87.5%
MMLU-Pro
83.0%
LiveCodeBench
81.2%
AIME 2025
85.0%
MATH-500
Humanity's Last Exam
12.7%26.6%
SciCode
37.5%49.9%
IFBench
41.4%73.3%
TerminalBench
25.0%52.3%
ERNIE 5.0 Thinking Preview4 wins
7 winsGPT-5.4 mini (xhigh)

Frequently Asked Questions

Which is cheaper, ERNIE 5.0 Thinking Preview or GPT-5.4 mini (xhigh)?

ERNIE 5.0 Thinking Preview is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $1.69/M for GPT-5.4 mini (xhigh).

Which model performs better on benchmarks?

GPT-5.4 mini (xhigh) wins 7 out of 12 benchmarks compared to 4 for ERNIE 5.0 Thinking Preview. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GPT-5.4 mini (xhigh) generates tokens faster at 219 tok/s vs 0 tok/s. ERNIE 5.0 Thinking Preview also has lower time-to-first-token (0.00s vs 3.82s).

When should I use ERNIE 5.0 Thinking Preview vs GPT-5.4 mini (xhigh)?

Choose based on your priorities: ERNIE 5.0 Thinking Preview for lower cost, GPT-5.4 mini (xhigh) for stronger benchmark performance, and GPT-5.4 mini (xhigh) for faster generation. For latency-sensitive apps, check the TTFT comparison above.