Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialogue Reasoning on DIPLOMAT
Loading...
168.2
AIBC Score
AutoMix + T
-14.008
33.296
80.6
127.904
Oct 19, 2023
AIBC Score
Updated 4d ago
Evaluation Results
Method
Method
Links
AIBC Score
AutoMix + T
SLM=GPT-3.5, Router=Th...
2023.10
168.2
AutoMix + P
SLM=MISTRAL-7B, Router...
2023.10
156.8
AutoMix + P
SLM=GPT-3.5, Router=PO...
2023.10
151.2
AutoMix + T
SLM=MISTRAL-7B, Router...
2023.10
149.7
HybridLLM
SLM=MISTRAL-7B
2023.10
67.1
AutoMix + P
SLM=LLAMA2-13B, Router...
2023.10
58.5
AutoMix + T
SLM=LLAMA2-13B, Router...
2023.10
50.1
FrugalGPT
SLM=GPT-3.5
2023.10
30.1
FrugalGPT
SLM=MISTRAL-7B
2023.10
16.8
HybridLLM
SLM=GPT-3.5
2023.10
8.3
HybridLLM
SLM=LLAMA2-13B
2023.10
3.8
FrugalGPT
SLM=LLAMA2-13B
2023.10
-7
Feedback
Search any
task
Search any
task