Key Takeaways
Mistral Small 24B Instruct 2501 wins:
- Larger context window
- Faster response time
- Better at math
- Supports tool calls
Llama 3 8B Lunaris wins:
- Cheaper input tokens
- Cheaper output tokens
- Higher intelligence benchmark
- Has reasoning mode
Price Advantage
Llama 3 8B Lunaris
Benchmark Advantage
Mistral Small 24B Instruct 2501
Context Window
Mistral Small 24B Instruct 2501
Speed
Mistral Small 24B Instruct 2501
Pricing Comparison
Price Comparison
| Metric | Mistral Small 24B Instruct 2501 | Llama 3 8B Lunaris | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.05 | $0.04 | Llama 3 8B Lunaris |
| Output (per 1M tokens) | $0.08 | $0.05 | Llama 3 8B Lunaris |
| Cache Read (per 1M) | $0.45 | N/A | Mistral Small 24B Instruct 2501 |
Using a 3:1 input/output ratio, Llama 3 8B Lunaris is 26% cheaper overall.
Mistral Small 24B Instruct 2501 Providers
No provider data available
Llama 3 8B Lunaris Providers
No provider data available
Benchmark Comparison
7
Benchmarks Compared
2
Mistral Small 24B Instruct 2501 Wins
1
Llama 3 8B Lunaris Wins
Benchmark Scores
| Benchmark | Mistral Small 24B Instruct 2501 | Llama 3 8B Lunaris | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 12.7 | 25.6 | |
Math Index Mathematical reasoning | 4.3 | - | - |
MMLU Pro Academic knowledge | 65.2 | 31.0 | |
GPQA Graduate-level science | 46.2 | 6.8 | |
LiveCodeBench Competitive programming | 25.2 | - | - |
AIME Competition math | 8.0 | - | - |
BBH Big-Bench Hard | - | 32.1 | - |
Mistral Small 24B Instruct 2501 wins 2 out of 7 benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Mistral Small 24B Instruct 2501
Other models
Context & Performance
Context Window
Mistral Small 24B Instruct 2501
32,768
tokens
Llama 3 8B Lunaris
8,192
tokens
Mistral Small 24B Instruct 2501 has a 75% larger context window.
Speed Performance
| Metric | Mistral Small 24B Instruct 2501 | Llama 3 8B Lunaris | Winner |
|---|---|---|---|
| Tokens/second | 180.9 tok/s | N/A | |
| Time to First Token | 0.32s | N/A |
Capabilities
Feature Comparison
| Feature | Mistral Small 24B Instruct 2501 | Llama 3 8B Lunaris |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Mistral Small 24B Instruct 2501 | Llama 3 8B Lunaris |
|---|---|---|
| License | Open Source | Open Source |
| Author | Mistral AI | Sao10k |
| Released | Jan 2025 | Aug 2024 |
Mistral Small 24B Instruct 2501 Modalities
Input
text
Output
text
Llama 3 8B Lunaris Modalities
Input
text
Output
text