LLM Hallucination Index RAG SpecialModel Insights
mistral-large-2402
Details
Developer
mistral
License
NA (private model)
Model parameters
NA (private model)
Supported context length
32k
Price for prompt token
$8/Million tokens
Price for response token
$24/Million tokens
Model Performance Across Task-Types
Chainpoll Score
Short Context
0.95
Medium Context
1
Model Insights Across Task-Types
Digging deeper, here’s a look how mistral-large-2402 performed across specific datasets
Short Context RAG
Medium Context RAG
This heatmap indicates the model's success in recalling information at different locations in the context. Green signifies success, while red indicates failure.
Performance Summary
| Tasks | Task insight | Cost insight | Dataset | Context adherence | Avg response length |
|---|---|---|---|---|---|
| Short context RAG | The model demonstrates exceptional reasoning and comprehension skills, excelling at short context RAG. It shows good mathematical proficiency, as evidenced by its performance on DROP and ConvFinQA benchmarks. | A very costly model with similar performance to Llama-3-70b and qwen2-72b. We do not recommend using this. | Drop | 0.94 | 353 |
| Hotpot | 0.93 | 353 | |||
| MS Marco | 0.95 | 353 | |||
| ConvFinQA | 0.97 | 353 | |||
| Medium context RAG | Flawless performance making it suitable for any context length upto 25000 tokens. | Great performance but we recommed using 70x cheaper Gemini Flash. | Medium context RAG | 1.00 | 353 |