NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-10-01-01J94RKE52P2PZW4XT8RHM1WNJ
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
You lift a freshly baked cinnamon roll to your nose, breathing in the sweet scent. "Delicious,"
you say, handing your husband the plate
. "We should have bought a dozen. I'll never get my fill." You watch him devour the roll. You pour him a mug of steaming coffee. "Easy there, sleepyhead,"
you tease
. He winks. "Alas, I can't sleep all day without having a heartattack." You sip your tea and page through the morning paper. An article about a spate of indecent exposure on the trail catches your eye. "Count me in for that bodybuilder meetup." The last few nights...it's all gone downhill, he moans after swallowing an awkward mouthful. A health plan change means the gym's $145 monthly rate. Plus estimated fuel costs for the extra commute. You halt the article. "Hold on, white-collar worker -- you're making $90/hr." "You did the numbers last time, remember?" "Yeah...I did. Emphatically. How that turned into $15k/year is beyond me. With all those moving parts I've learned only two things: we shouldn't borrow on home equity, and we need to eat well."
id
"gen-1727810615-V24JKvNznxBTsrotEmjU"
total_cost
0.0001465
upstream_id
"chatcmpl-b6837969-39b2-4108-920a-199d5b2fbe3a"
created_at
"2024-10-01T19:23:47.871204+00:00"
Tuesday, October 1st, 2024 at 7:23:47 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
53
moderation_latency
(null)
generation_time
11985
finish_reason
"stop"
tokens_prompt
68
tokens_completion
253
native_tokens_prompt
72
native_tokens_completion
257
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001465
Evaluation details
Result
Evaluator
Details
Meta Data
13.5335%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"you say, handing your husband the plate"
1
"you tease"