Price Per TokenPrice Per Token
Baidu
Baidu
vs
OpenAI
OpenAI

ERNIE 4.5 21B A3B Thinking vs GPT-OSS-120b

A detailed comparison of pricing, benchmarks, and capabilities

Best Coding Model Leaderboard Find the top LLM for coding by benchmarks and community votes

114 out of our 298 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

ERNIE 4.5 21B A3B Thinking wins:

  • Has reasoning mode
  • Supports tool calls

GPT-OSS-120b wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
Price Advantage
GPT-OSS-120b
Benchmark Advantage
GPT-OSS-120b
Context Window
GPT-OSS-120b
Speed
GPT-OSS-120b

Pricing Comparison

Price Comparison

MetricERNIE 4.5 21B A3B ThinkingGPT-OSS-120bWinner
Input (per 1M tokens)$0.07$0.04 GPT-OSS-120b
Output (per 1M tokens)$0.28$0.19 GPT-OSS-120b
Using a 3:1 input/output ratio, GPT-OSS-120b is 37% cheaper overall.

ERNIE 4.5 21B A3B Thinking Providers

Novita $0.07 (Cheapest)

GPT-OSS-120b Providers

Chutes $0.04 (Cheapest)
SiliconFlow $0.05
Novita $0.05
NCompass $0.05
Clarifai $0.09

Benchmark Comparison

7
Benchmarks Compared
0
ERNIE 4.5 21B A3B Thinking Wins
0
GPT-OSS-120b Wins

Benchmark Scores

BenchmarkERNIE 4.5 21B A3B ThinkingGPT-OSS-120bWinner
Intelligence Index
Overall intelligence score
-33.3-
Coding Index
Code generation & understanding
-28.6-
Math Index
Mathematical reasoning
-93.4-
MMLU Pro
Academic knowledge
-80.8-
GPQA
Graduate-level science
-78.2-
LiveCodeBench
Competitive programming
-87.8-
Aider
Real-world code editing
-41.8-
GPT-OSS-120b significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Other models

Context & Performance

Context Window

ERNIE 4.5 21B A3B Thinking
131,072
tokens
Max output: 65,536 tokens
GPT-OSS-120b
131,072
tokens

Speed Performance

MetricERNIE 4.5 21B A3B ThinkingGPT-OSS-120bWinner
Tokens/secondN/A327.2 tok/s
Time to First TokenN/A0.48s

Capabilities

Feature Comparison

FeatureERNIE 4.5 21B A3B ThinkingGPT-OSS-120b
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyERNIE 4.5 21B A3B ThinkingGPT-OSS-120b
LicenseOpen SourceOpen Source
AuthorBaiduOpenAI
ReleasedOct 2025Aug 2025

ERNIE 4.5 21B A3B Thinking Modalities

Input
text
Output
text

GPT-OSS-120b Modalities

Input
text
Output
text

Related Comparisons

Compare ERNIE 4.5 21B A3B Thinking with:

Compare GPT-OSS-120b with:

Frequently Asked Questions

GPT-OSS-120b has cheaper input pricing at $0.04/M tokens. GPT-OSS-120b has cheaper output pricing at $0.19/M tokens.
GPT-OSS-120b scores higher on coding benchmarks with a score of 28.6, compared to ERNIE 4.5 21B A3B Thinking's score of N/A.
ERNIE 4.5 21B A3B Thinking has a 131,072 token context window, while GPT-OSS-120b has a 131,072 token context window.
ERNIE 4.5 21B A3B Thinking does not support vision. GPT-OSS-120b does not support vision.