Key Takeaways
Phi-3 Mini 128K Instruct wins:
- Higher intelligence benchmark
Mistral Nemo wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
Price Advantage
Mistral Nemo
Benchmark Advantage
Phi-3 Mini 128K Instruct
Context Window
Mistral Nemo
Speed
N/A
Pricing Comparison
Price Comparison
| Metric | Phi-3 Mini 128K Instruct | Mistral Nemo | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.10 | $0.02 | Mistral Nemo |
| Output (per 1M tokens) | $0.10 | $0.04 | Mistral Nemo |
| Cache Read (per 1M) | N/A | $0.01 | Mistral Nemo |
Using a 3:1 input/output ratio, Mistral Nemo is 75% cheaper overall.
Phi-3 Mini 128K Instruct Providers
No provider data available
Mistral Nemo Providers
No provider data available
Benchmark Comparison
4
Benchmarks Compared
3
Phi-3 Mini 128K Instruct Wins
0
Mistral Nemo Wins
Benchmark Scores
| Benchmark | Phi-3 Mini 128K Instruct | Mistral Nemo | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 26.3 | 25.0 | |
MMLU Pro Academic knowledge | 30.4 | 26.4 | |
GPQA Graduate-level science | 9.1 | 8.7 | - |
BBH Big-Bench Hard | 37.1 | 36.1 |
Phi-3 Mini 128K Instruct wins 3 out of 4 benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Phi-3 Mini 128K Instruct
Other models
Context & Performance
Context Window
Phi-3 Mini 128K Instruct
128,000
tokens
Mistral Nemo
131,072
tokens
Mistral Nemo has a 2% larger context window.
Speed Performance
Speed benchmarks not available for these models
Capabilities
Feature Comparison
| Feature | Phi-3 Mini 128K Instruct | Mistral Nemo |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Phi-3 Mini 128K Instruct | Mistral Nemo |
|---|---|---|
| License | Open Source | Open Source |
| Author | Microsoft | Mistral AI |
| Released | Unknown | Jul 2024 |
Phi-3 Mini 128K Instruct Modalities
Input
Output
Mistral Nemo Modalities
Input
text
Output
text