Compare/ERNIE 4.5 300B A47B vs Llama 3.1 Nemotron Instruct 70B

ERNIE 4.5 300B A47BvsLlama 3.1 Nemotron Instruct 70B

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

Baidu

ERNIE 4.5 300B A47B

Input
$0.28/M
Output
$1.1/M
Speed
30 tok/s
TTFT
1.90s
NVIDIA

Llama 3.1 Nemotron Instruct 70B

Input
$1.2/M
Output
$1.2/M
Speed
33 tok/s
TTFT
0.39s

Winner by Category

Cheaper
ERNIE 4.5 300B A47B
Faster (tok/s)
Llama 3.1 Nemotron Instruct 70B
Lower Latency
Llama 3.1 Nemotron Instruct 70B
Benchmarks (11-1)
ERNIE 4.5 300B A47B

Pricing Comparison

MetricERNIE 4.5 300B A47BLlama 3.1 Nemotron Instruct 70B
Input ($/M tokens)$0.28$1.2
Output ($/M tokens)$1.1$1.2
Cost for 1M input + 100K output tokens:
ERNIE 4.5 300B A47B$0.39
Llama 3.1 Nemotron Instruct 70B$1.32

Speed Comparison

Output Speed (tokens/s) — higher is better
ERNIE 4.5 300B A47B
30 tok/s
Llama 3.1 Nemotron Instruct 70B
33 tok/s
Time to First Token (seconds) — lower is better
ERNIE 4.5 300B A47B
1.90s
Llama 3.1 Nemotron Instruct 70B
0.39s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
15.013.4
Coding Index
14.510.8
Math Index
41.311.0
GPQA Diamond
81.1%46.5%
MMLU-Pro
77.6%69.0%
LiveCodeBench
46.7%16.9%
AIME 2025
41.3%11.0%
MATH-500
93.1%73.3%
Humanity's Last Exam
3.5%4.6%
SciCode
31.5%23.3%
IFBench
39.1%30.7%
TerminalBench
6.1%4.5%
ERNIE 4.5 300B A47B11 wins
1 winsLlama 3.1 Nemotron Instruct 70B

Frequently Asked Questions

Which is cheaper, ERNIE 4.5 300B A47B or Llama 3.1 Nemotron Instruct 70B?

ERNIE 4.5 300B A47B is cheaper overall. Its blended price (3:1 input/output ratio) is $0.48/M tokens vs $1.20/M for Llama 3.1 Nemotron Instruct 70B.

Which model performs better on benchmarks?

ERNIE 4.5 300B A47B wins 11 out of 12 benchmarks compared to 1 for Llama 3.1 Nemotron Instruct 70B. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Llama 3.1 Nemotron Instruct 70B generates tokens faster at 33 tok/s vs 30 tok/s. However, Llama 3.1 Nemotron Instruct 70B has lower time-to-first-token (0.39s vs 1.90s).

When should I use ERNIE 4.5 300B A47B vs Llama 3.1 Nemotron Instruct 70B?

Choose based on your priorities: ERNIE 4.5 300B A47B for lower cost, ERNIE 4.5 300B A47B for stronger benchmark performance, and Llama 3.1 Nemotron Instruct 70B for faster generation. For latency-sensitive apps, check the TTFT comparison above.