Price Per TokenPrice Per Token
Mistral AI
Mistral AI
vs
Qwen
Qwen

Devstral 2 2512 vs Qwen2.5 7B Instruct

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

100 out of our 304 tracked models have had a price change in February.

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

Key Takeaways

Devstral 2 2512 wins:

  • Larger context window
  • Faster response time
  • Better at coding
  • Better at math

Qwen2.5 7B Instruct wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Higher intelligence benchmark
Price Advantage
Qwen2.5 7B Instruct
Benchmark Advantage
Devstral 2 2512
Context Window
Devstral 2 2512
Speed
Devstral 2 2512

Pricing Comparison

Price Comparison

MetricDevstral 2 2512Qwen2.5 7B InstructWinner
Input (per 1M tokens)$0.05$0.04 Qwen2.5 7B Instruct
Output (per 1M tokens)$0.22$0.10 Qwen2.5 7B Instruct
Using a 3:1 input/output ratio, Qwen2.5 7B Instruct is 41% cheaper overall.

Devstral 2 2512 Providers

Chutes $0.05 (Cheapest)
Mistral $0.40

Qwen2.5 7B Instruct Providers

Phala $0.04 (Cheapest)
AtlasCloud $0.04 (Cheapest)
Together $0.30

Benchmark Comparison

7
Benchmarks Compared
2
Devstral 2 2512 Wins
1
Qwen2.5 7B Instruct Wins

Benchmark Scores

BenchmarkDevstral 2 2512Qwen2.5 7B InstructWinner
Intelligence Index
Overall intelligence score
22.035.2
Coding Index
Code generation & understanding
23.7--
Math Index
Mathematical reasoning
36.7--
MMLU Pro
Academic knowledge
76.236.5
GPQA
Graduate-level science
59.45.5
LiveCodeBench
Competitive programming
44.8--
BBH
Big-Bench Hard
-34.9-
Devstral 2 2512 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Devstral 2 2512
Other models

Context & Performance

Context Window

Devstral 2 2512
262,144
tokens
Max output: 65,536 tokens
Qwen2.5 7B Instruct
32,768
tokens
Devstral 2 2512 has a 88% larger context window.

Speed Performance

MetricDevstral 2 2512Qwen2.5 7B InstructWinner
Tokens/second64.0 tok/sN/A
Time to First Token0.41sN/A

Capabilities

Feature Comparison

FeatureDevstral 2 2512Qwen2.5 7B Instruct
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyDevstral 2 2512Qwen2.5 7B Instruct
LicenseOpen SourceOpen Source
AuthorMistral AIQwen
ReleasedDec 2025Oct 2024

Devstral 2 2512 Modalities

Input
text
Output
text

Qwen2.5 7B Instruct Modalities

Input
text
Output
text

Related Comparisons

Compare Devstral 2 2512 with:

Compare Qwen2.5 7B Instruct with:

Frequently Asked Questions

Qwen2.5 7B Instruct has cheaper input pricing at $0.04/M tokens. Qwen2.5 7B Instruct has cheaper output pricing at $0.10/M tokens.
Devstral 2 2512 scores higher on coding benchmarks with a score of 23.7, compared to Qwen2.5 7B Instruct's score of N/A.
Devstral 2 2512 has a 262,144 token context window, while Qwen2.5 7B Instruct has a 32,768 token context window.
Devstral 2 2512 does not support vision. Qwen2.5 7B Instruct does not support vision.