Key Takeaways
Mistral Small 3.1 24B wins:
- Cheaper input tokens
- Larger context window
- Faster response time
- Better at coding
- Better at math
- Supports vision
Qwen2.5 7B Instruct wins:
- Cheaper output tokens
- Higher intelligence benchmark
Price Advantage
Mistral Small 3.1 24B
Benchmark Advantage
Mistral Small 3.1 24B
Context Window
Mistral Small 3.1 24B
Speed
Mistral Small 3.1 24B
Pricing Comparison
Price Comparison
| Metric | Mistral Small 3.1 24B | Qwen2.5 7B Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.03 | $0.04 | Mistral Small 3.1 24B |
| Output (per 1M tokens) | $0.11 | $0.10 | Qwen2.5 7B Instruct |
| Cache Read (per 1M) | $15000.00 | N/A | Mistral Small 3.1 24B |
Using a 3:1 input/output ratio, Mistral Small 3.1 24B is 9% cheaper overall.
Mistral Small 3.1 24B Providers
Chutes $0.03 (Cheapest)
Cloudflare $0.35
Qwen2.5 7B Instruct Providers
Phala $0.04 (Cheapest)
AtlasCloud $0.04 (Cheapest)
Together $0.30
Benchmark Comparison
8
Benchmarks Compared
2
Mistral Small 3.1 24B Wins
1
Qwen2.5 7B Instruct Wins
Benchmark Scores
| Benchmark | Mistral Small 3.1 24B | Qwen2.5 7B Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 14.0 | 35.2 | |
Coding Index Code generation & understanding | 13.9 | - | - |
Math Index Mathematical reasoning | 3.7 | - | - |
MMLU Pro Academic knowledge | 65.9 | 36.5 | |
GPQA Graduate-level science | 45.4 | 5.5 | |
LiveCodeBench Competitive programming | 21.2 | - | - |
AIME Competition math | 9.3 | - | - |
BBH Big-Bench Hard | - | 34.9 | - |
Mistral Small 3.1 24B significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Mistral Small 3.1 24B
Other models
Context & Performance
Context Window
Mistral Small 3.1 24B
131,072
tokens
Max output: 131,072 tokens
Qwen2.5 7B Instruct
32,768
tokens
Mistral Small 3.1 24B has a 75% larger context window.
Speed Performance
| Metric | Mistral Small 3.1 24B | Qwen2.5 7B Instruct | Winner |
|---|---|---|---|
| Tokens/second | 104.2 tok/s | N/A | |
| Time to First Token | 0.29s | N/A |
Capabilities
Feature Comparison
| Feature | Mistral Small 3.1 24B | Qwen2.5 7B Instruct |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Mistral Small 3.1 24B | Qwen2.5 7B Instruct |
|---|---|---|
| License | Open Source | Open Source |
| Author | Mistral AI | Qwen |
| Released | Mar 2025 | Oct 2024 |
Mistral Small 3.1 24B Modalities
Input
textimage
Output
text
Qwen2.5 7B Instruct Modalities
Input
text
Output
text