Price Per TokenPrice Per Token
Microsoft
Microsoft
vs
Mistral AI
Mistral AI

WizardLM-2 8x22B vs Devstral 2 2512

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

WizardLM-2 8x22B wins:

  • Cheaper output tokens
  • Higher intelligence benchmark

Devstral 2 2512 wins:

  • Cheaper input tokens
  • Larger context window
  • Faster response time
  • Better at coding
  • Better at math
Price Advantage
WizardLM-2 8x22B
Benchmark Advantage
Devstral 2 2512
Context Window
Devstral 2 2512
Speed
Devstral 2 2512

Pricing Comparison

Price Comparison

MetricWizardLM-2 8x22BDevstral 2 2512Winner
Input (per 1M tokens)$0.62$0.40 Devstral 2 2512
Output (per 1M tokens)$0.62$0.90 WizardLM-2 8x22B
Cache Read (per 1M)N/A$0.45 Devstral 2 2512
Using a 3:1 input/output ratio, Devstral 2 2512 is 15% cheaper overall.

WizardLM-2 8x22B Providers

No provider data available

Devstral 2 2512 Providers

No provider data available

Benchmark Comparison

8
Benchmarks Compared
1
WizardLM-2 8x22B Wins
2
Devstral 2 2512 Wins

Benchmark Scores

BenchmarkWizardLM-2 8x22BDevstral 2 2512Winner
Intelligence Index
Overall intelligence score
33.122.0
Coding Index
Code generation & understanding
-23.7-
Math Index
Mathematical reasoning
-36.7-
MMLU Pro
Academic knowledge
40.076.2
GPQA
Graduate-level science
17.659.4
LiveCodeBench
Competitive programming
-44.8-
Aider
Real-world code editing
44.4--
BBH
Big-Bench Hard
48.6--
Devstral 2 2512 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
WizardLM-2 8x22B
Other models

Context & Performance

Context Window

WizardLM-2 8x22B
65,535
tokens
Devstral 2 2512
262,144
tokens
Devstral 2 2512 has a 75% larger context window.

Speed Performance

MetricWizardLM-2 8x22BDevstral 2 2512Winner
Tokens/secondN/A81.2 tok/s
Time to First TokenN/A0.39s

Capabilities

Feature Comparison

FeatureWizardLM-2 8x22BDevstral 2 2512
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyWizardLM-2 8x22BDevstral 2 2512
LicenseOpen SourceOpen Source
AuthorMicrosoftMistral AI
ReleasedApr 2024Dec 2025

WizardLM-2 8x22B Modalities

Input
text
Output
text

Devstral 2 2512 Modalities

Input
text
Output
text

Related Comparisons

Compare WizardLM-2 8x22B with:

Compare Devstral 2 2512 with:

Frequently Asked Questions

Devstral 2 2512 has cheaper input pricing at $0.40/M tokens. WizardLM-2 8x22B has cheaper output pricing at $0.62/M tokens.
Devstral 2 2512 scores higher on coding benchmarks with a score of 23.7, compared to WizardLM-2 8x22B's score of N/A.
WizardLM-2 8x22B has a 65,535 token context window, while Devstral 2 2512 has a 262,144 token context window.
WizardLM-2 8x22B does not support vision. Devstral 2 2512 does not support vision.