Compare/DeepSeek V3 0324 vs ERNIE 4.5 300B A47B

DeepSeek V3 0324vsERNIE 4.5 300B A47B

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

DeepSeek

DeepSeek V3 0324

Input
$0.27/M
Output
$1.12/M
Speed
TTFT
Baidu

ERNIE 4.5 300B A47B

Input
$0.28/M
Output
$1.1/M
Speed
TTFT

Winner by Category

Cheaper
DeepSeek V3 0324
Faster (tok/s)
Lower Latency
Benchmarks (2-0)
DeepSeek V3 0324

Pricing Comparison

MetricDeepSeek V3 0324ERNIE 4.5 300B A47B
Input ($/M tokens)$0.27$0.28
Output ($/M tokens)$1.12$1.1
Cost for 1M input + 100K output tokens:
DeepSeek V3 0324$0.38
ERNIE 4.5 300B A47B$0.39

Speed Comparison

Speed data not available for these models.

Editorial Analysis

Verdict. DeepSeek V3 0324 wins the overall benchmark matchup 2–0 across 2 overlapping categories, but raw benchmark score is only one input to the decision.

Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, ERNIE 4.5 300B A47B is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). ERNIE 4.5 300B A47B makes more sense when output volume is low and absolute reasoning quality justifies the premium.

Strengths. DeepSeek V3 0324 is strongest on Coding Index (21.2), Intelligence Index (15.2). ERNIE 4.5 300B A47B leads on Intelligence Index (8.9).

Speed. Speed data is incomplete for this pair; benchmark and price should decide.

Provider. DeepSeek and Baidu sell to overlapping but distinct developer audiences: DeepSeek tends to ship frontier reasoning models with premium positioning, while Baidu often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.

Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): DeepSeek V3 0324 costs $24.90 ($299/year); ERNIE 4.5 300B A47B costs $24.90 ($299/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): DeepSeek V3 0324 ≈ $3.59/run, ERNIE 4.5 300B A47B ≈ $3.60/run. At agent/realtime scale (200M input / 100M output per million requests): DeepSeek V3 0324 ≈ $166/run, ERNIE 4.5 300B A47B ≈ $166/run.

Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
15.28.9
Coding Index
21.2
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
DeepSeek V3 03242 wins
0 winsERNIE 4.5 300B A47B

Frequently Asked Questions

Which is cheaper, DeepSeek V3 0324 or ERNIE 4.5 300B A47B?

DeepSeek V3 0324 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.48/M tokens vs $0.48/M for ERNIE 4.5 300B A47B.

Which model performs better on benchmarks?

DeepSeek V3 0324 wins 2 out of 12 benchmarks compared to 0 for ERNIE 4.5 300B A47B. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Both models have comparable generation speeds.

When should I use DeepSeek V3 0324 vs ERNIE 4.5 300B A47B?

Choose based on your priorities: DeepSeek V3 0324 for lower cost, DeepSeek V3 0324 for stronger benchmark performance, and both have comparable speed. For latency-sensitive apps, check the TTFT comparison above.