Model

WizardLM 2 8x22b

Test

Data extraction

Scenario

Contextual pronoun

Run ID

2024-07-12-01J2KK2BE761YF0G71CMQMR990

Model input

User/Human
Who does "he" refer to in the last sentence? Only return the name. Tom and Jerry were playing in the yard. Spike, the dog, was watching them from his kennel. Suddenly, he started barking loudly.

Model response

AI
Spike
id"gen-KE0dRR7oaK67JmBHGi0vGHuyQfCv" 
total_cost0.00005888
upstream_id"cmpl-085b06f0a07d4b3b803624dd9f53ec48" 
created_at"2024-07-12T13:45:39.920577+00:00" Friday, July 12th, 2024 at 1:45:39 PM GMT+00:00
model"microsoft/wizardlm-2-8x22b" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Novita" 
latency547
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt81
tokens_completion2
native_tokens_prompt89
native_tokens_completion3
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.00005888

Evaluation details

Result Evaluator Details Meta Data
Pass Matches text
Case sensitive: Spike
n/a
Pass Matches Regex
/\bSpike\b/
n/a
100.0000%