Details
Developer
Mistral
License
NA (private model)
Model parameters
NA (private model)
Supported context length
128k
Price for prompt token
$2/Million tokens
Price for response token
$6/Million tokens
Chainpoll Score
Short Context
0.96
Medium Context
0.99
Long Context
0.78
Digging deeper, here’s a look how mistral-large-2407 performed across specific datasets
This heatmap indicates the model's success in recalling information at different locations in the context. Green signifies success, while red indicates failure.
This heatmap indicates the model's success in recalling information at different locations in the context. Green signifies success, while red indicates failure.
Tasks | Dataset | Context adherence | Avg response length |
---|---|---|---|
Short context RAG | Drop | 0.96 | 209.8 |
Hotpot | 0.93 | 138.3 | |
MS Marco | 0.97 | 646.8 | |
ConvFinQA | 0.98 | 421.4 | |
Medium context RAG | Medium context RAG | 0.99 | NA |
Long context RAG | Long context RAG | 0.78 | NA |