Run: 2024-09-20-01J881C07PCWWF8CD37ARGGY82

Run Details

Model:
Qwen 2.5 72B
Test:
Data extraction
Scenario:
What's the color of the car?
Duration:
675ms
Cost:
$0.000032
Provider:
Hyperbolic

Evaluation summary

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

Model input

User/Human
What color is Sarah's car based on the following text? Only return the color, nothing else. John owns a blue car. Sarah's car is the same color as the sky on a clear day. Peter's car is red. The sky is not green on a clear day.

Model response

AI
blue
id"gen-hFuU9CT0CshBrokkrgCUmtSujxp2"
total_cost0.0000316
upstream_id"chat-7671fd22e19044b18034b9460d66ee1d"
created_at"2024-09-20T15:38:51.486955+00:00" 9/20/2024, 3:38:51 PM
model"qwen/qwen-2.5-72b-instruct"
app_id182717
streamedtrue
cancelledfalse
provider_name"Hyperbolic"
latency499
moderation_latency(null)
generation_time32
finish_reason"stop"
tokens_prompt74
tokens_completion1
native_tokens_prompt76
native_tokens_completion3
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/"
usage0.0000316

Evaluation details

Result Evaluator Details Meta Data
Pass Matches text
Case insensitive: blue
 n/a
Pass Matches Regex
/\bblue\b/i
 n/a
no eval