Price Per TokenPrice Per Token
OpenAI
OpenAI
vs
Qwen
Qwen

GPT-OSS-120b vs Qwen3 Max

A detailed comparison of pricing, benchmarks, and capabilities

Sponsor Price Per Token Reach 5000+ developers comparing LLM APIs

116 out of our 296 tracked models have had a price change in January.

Make informed model choices with updates on pricing, new releases, and tools with our weekly newsletter.

Key Takeaways

GPT-OSS-120b wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math

Qwen3 Max wins:

  • Larger context window
  • Supports tool calls
Price Advantage
GPT-OSS-120b
Benchmark Advantage
GPT-OSS-120b
Context Window
Qwen3 Max
Speed
GPT-OSS-120b

Pricing Comparison

Price Comparison

MetricGPT-OSS-120bQwen3 MaxWinner
Input (per 1M tokens)$0.04$1.20 GPT-OSS-120b
Output (per 1M tokens)$0.19$6.00 GPT-OSS-120b
Cache Read (per 1M)N/A$240000.00 Qwen3 Max
Using a 3:1 input/output ratio, GPT-OSS-120b is 97% cheaper overall.

GPT-OSS-120b Providers

GMICloud $0.02 (Cheapest)
Chutes $0.04
OpenRouter $0.04
SiliconFlow $0.05
NCompass $0.05

Qwen3 Max Providers

OpenRouter $1.20 (Cheapest)
Alibaba $1.20 (Cheapest)

Benchmark Comparison

7
Benchmarks Compared
5
GPT-OSS-120b Wins
1
Qwen3 Max Wins

Benchmark Scores

BenchmarkGPT-OSS-120bQwen3 MaxWinner
Intelligence Index
Overall intelligence score
32.931.0
Coding Index
Code generation & understanding
27.625.5
Math Index
Mathematical reasoning
93.480.7
MMLU Pro
Academic knowledge
80.884.1
GPQA
Graduate-level science
78.276.4
LiveCodeBench
Competitive programming
87.876.7
Aider
Real-world code editing
41.8--
GPT-OSS-120b shows stronger mathematical reasoning abilities.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
GPT-OSS-120b
Other models

Context & Performance

Context Window

GPT-OSS-120b
131,072
tokens
Qwen3 Max
256,000
tokens
Max output: 32,768 tokens
Qwen3 Max has a 49% larger context window.

Speed Performance

MetricGPT-OSS-120bQwen3 MaxWinner
Tokens/second337.9 tok/s24.5 tok/s
Time to First Token0.42s1.90s
GPT-OSS-120b responds 1282% faster on average.

Capabilities

Feature Comparison

FeatureGPT-OSS-120bQwen3 Max
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyGPT-OSS-120bQwen3 Max
LicenseOpen SourceOpen Source
AuthorOpenAIQwen
ReleasedAug 2025Sep 2025

GPT-OSS-120b Modalities

Input
text
Output
text

Qwen3 Max Modalities

Input
text
Output
text

Related Comparisons

Compare GPT-OSS-120b with:

Compare Qwen3 Max 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 27.6, compared to Qwen3 Max's score of 25.5.
GPT-OSS-120b has a 131,072 token context window, while Qwen3 Max has a 256,000 token context window.
GPT-OSS-120b does not support vision. Qwen3 Max does not support vision.