Run: 2024-10-16-01JABHYXK2APK1SJK4T5V2PHVE

Run Details

Model:
Llama 3.1 Nemotron 70B
Test:
Data extraction
Scenario:
Contextual pronoun
Duration:
423ms
Cost:
$0.000021
Provider:
DeepInfra

Evaluation summary

Score Evaluator
Details Link
Pass Matches text (details)
Pass Matches Regex (details)
no eval Overall

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-1729112274-RX7a17e7pKGZDlHLyOhf"
upstream_id"cmpl-R6GpRQAmouHTr7CMmgKwadPl"
total_cost0.00002075
cache_discount(null)
created_at"2024-10-16T20:57:55.52135+00:00" 10/16/2024, 8:57:55 PM
model"nvidia/llama-3.1-nemotron-70b-instruct"
app_id182717
streamedtrue
cancelledfalse
provider_name"DeepInfra"
latency86
moderation_latency(null)
generation_time236
finish_reason"stop"
tokens_prompt88
tokens_completion2
native_tokens_prompt57
native_tokens_completion2
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/"
usage0.00002075

Evaluation details

Result Evaluator Details Meta Data
Pass Matches text
Case sensitive: Spike
 n/a
Pass Matches Regex
/\bSpike\b/
 n/a
no eval