weave-cookboook-demo Workspace – Weights & Biases

Skip to main content

Evaluations

Filter

inputs

output

model_latency

Performance Metrics

Safety Metrics

Correctness

No Hallucination

Trace

Feedback

Status

model

self

mean

claude-3-haiku-20240307

gpt-4o-mini

Total Avg

Nr1_Retrieval

claude-3-haiku-20240307

Bedrock Mixtral-8x7b-Instruct

climate_rag_eval:v0

18.2765

0.8889

0.5556

0.7222

0

1

Bedrock Cohere-Command-v14

climate_rag_eval:v0

24.092

0.8889

0.3333

0.6111

0

0.8889

Bedrock Claude-3-Sonnet

climate_rag_eval:v0

16.9215

0.8889

0.2222

0.5556

0

0.8889

Custom Llama-3.2 LoRA Unsloth

climate_rag_eval:v0

5.0778

0.8889

0.3333

0.6111

0

0.4444

Custom Llama-3.2 3B

climate_rag_eval:v0

116.741

0.8889

0.2222

0.5556

0

0.8889

Custom Llama-3.2 1B

climate_rag_eval:v0

10.2769

1

0.3333

0.6667

0

0.8889

Gemini-1.5-Flash User Feedback

gen_eval_dataset-evaluation:v1

3.1515

0.5556

0.2222

0.3889

0.6667

0.6667

Gemini-1.5-Flash Test

gen_eval_dataset-evaluation:v0

3.0972

0.8571

0.1429

0.5

0.7143

0.7143

Claude3-Haiku Test

gen_eval_dataset-evaluation:v0

2.5219

0.8571

0.4286

0.6429

0.7143

0.8571

GPT4o-Mini Test - v1

gen_eval_dataset-evaluation:v0

4.8782

0.7143

0.1429

0.4286

0.7143

0.8571

gen_eval_dataset-evaluation:v0

4.8997

0.5714

0.1429

0.3571

0.7143

0.8571

1-11

of 11