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

Phi-3 Medium 128K Instruct 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

Phi-3 Medium 128K Instruct wins:

  • Higher intelligence benchmark

Devstral 2 2512 wins:

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

Pricing Comparison

Price Comparison

MetricPhi-3 Medium 128K InstructDevstral 2 2512Winner
Input (per 1M tokens)$1.00$0.40 Devstral 2 2512
Output (per 1M tokens)$1.00$0.90 Devstral 2 2512
Cache Read (per 1M)N/A$0.45 Devstral 2 2512
Using a 3:1 input/output ratio, Devstral 2 2512 is 48% cheaper overall.

Phi-3 Medium 128K Instruct Providers

No provider data available

Devstral 2 2512 Providers

No provider data available

Benchmark Comparison

7
Benchmarks Compared
1
Phi-3 Medium 128K Instruct Wins
2
Devstral 2 2512 Wins

Benchmark Scores

BenchmarkPhi-3 Medium 128K InstructDevstral 2 2512Winner
Intelligence Index
Overall intelligence score
32.022.0
Coding Index
Code generation & understanding
-23.7-
Math Index
Mathematical reasoning
-36.7-
MMLU Pro
Academic knowledge
41.276.2
GPQA
Graduate-level science
11.559.4
LiveCodeBench
Competitive programming
-44.8-
BBH
Big-Bench Hard
48.5--
Devstral 2 2512 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
Devstral 2 2512
262,144
tokens
Devstral 2 2512 has a 51% larger context window.

Speed Performance

MetricPhi-3 Medium 128K InstructDevstral 2 2512Winner
Tokens/secondN/A81.2 tok/s
Time to First TokenN/A0.39s

Capabilities

Feature Comparison

FeaturePhi-3 Medium 128K InstructDevstral 2 2512
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyPhi-3 Medium 128K InstructDevstral 2 2512
LicenseOpen SourceOpen Source
AuthorMicrosoftMistral AI
ReleasedUnknownDec 2025

Phi-3 Medium 128K Instruct Modalities

Input
Output

Devstral 2 2512 Modalities

Input
text
Output
text

Related Comparisons

Compare Phi-3 Medium 128K Instruct with:

Compare Devstral 2 2512 with:

Frequently Asked Questions

Devstral 2 2512 has cheaper input pricing at $0.40/M tokens. Devstral 2 2512 has cheaper output pricing at $0.90/M tokens.
Devstral 2 2512 scores higher on coding benchmarks with a score of 23.7, 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 Devstral 2 2512 has a 262,144 token context window.
Phi-3 Medium 128K Instruct does not support vision. Devstral 2 2512 does not support vision.