Price Per TokenPrice Per Token
Microsoft
Microsoft
vs
Qwen
Qwen

Phi-3 Medium 128K Instruct vs Qwen3.5-122B-A10B

A detailed comparison of pricing, benchmarks, and capabilities

108 out of our 483 tracked models have had a price change in March.

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

Key Takeaways

Phi-3 Medium 128K Instruct wins:

  • Cheaper output tokens

Qwen3.5-122B-A10B wins:

  • Cheaper input tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Supports vision
Price Advantage
Phi-3 Medium 128K Instruct
Benchmark Advantage
Qwen3.5-122B-A10B
Context Window
Qwen3.5-122B-A10B
Speed
Qwen3.5-122B-A10B

Pricing Comparison

Price Comparison

MetricPhi-3 Medium 128K InstructQwen3.5-122B-A10BWinner
Input (per 1M tokens)$1.00$0.26 Qwen3.5-122B-A10B
Output (per 1M tokens)$1.00$2.08 Phi-3 Medium 128K Instruct
Cache Read (per 1M)N/A$0.30 Qwen3.5-122B-A10B
Using a 3:1 input/output ratio, Qwen3.5-122B-A10B is 28% cheaper overall.

Phi-3 Medium 128K Instruct Providers

No provider data available

Qwen3.5-122B-A10B Providers

No provider data available

Benchmark Comparison

5
Benchmarks Compared
0
Phi-3 Medium 128K Instruct Wins
2
Qwen3.5-122B-A10B Wins

Benchmark Scores

BenchmarkPhi-3 Medium 128K InstructQwen3.5-122B-A10BWinner
Intelligence Index
Overall intelligence score
32.035.9
Coding Index
Code generation & understanding
-31.6-
MMLU Pro
Academic knowledge
41.2--
GPQA
Graduate-level science
11.582.7
BBH
Big-Bench Hard
48.5--
Qwen3.5-122B-A10B significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Phi-3 Medium 128K Instruct
Other models

Context & Performance

Context Window

Phi-3 Medium 128K Instruct
128,000
tokens
Qwen3.5-122B-A10B
262,144
tokens
Qwen3.5-122B-A10B has a 51% larger context window.

Speed Performance

MetricPhi-3 Medium 128K InstructQwen3.5-122B-A10BWinner
Tokens/secondN/A146.6 tok/s
Time to First TokenN/A1.03s

Capabilities

Feature Comparison

FeaturePhi-3 Medium 128K InstructQwen3.5-122B-A10B
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyPhi-3 Medium 128K InstructQwen3.5-122B-A10B
LicenseOpen SourceOpen Source
AuthorMicrosoftQwen
ReleasedUnknownFeb 2026

Phi-3 Medium 128K Instruct Modalities

Input
Output

Qwen3.5-122B-A10B Modalities

Input
textimagevideo
Output
text

Related Comparisons

Compare Phi-3 Medium 128K Instruct with:

Compare Qwen3.5-122B-A10B with:

Frequently Asked Questions

Qwen3.5-122B-A10B has cheaper input pricing at $0.26/M tokens. Phi-3 Medium 128K Instruct has cheaper output pricing at $1.00/M tokens.
Qwen3.5-122B-A10B scores higher on coding benchmarks with a score of 31.6, compared to Phi-3 Medium 128K Instruct's score of N/A.
Phi-3 Medium 128K Instruct has a 128,000 token context window, while Qwen3.5-122B-A10B has a 262,144 token context window.
Phi-3 Medium 128K Instruct does not support vision. Qwen3.5-122B-A10B supports vision.