NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Language Writing
Scenario
Character dialogue (French) in a story
Run ID
2024-10-01-01J94R8AX9T7H4NHPCKPY1JW02
Model input
System
You are an expert novel author in the cozy mystery genre. Take the following details about characters/locations/... into account: <character name="Marie"> Marie is a 30-year old college student on a study abroad program. Born in France, she is fluent in French and does not yet know any English. She enjoys landscape photography and is always seen with her camera. </character> <character name="Hunter"> Hunter is a 35-year old detective who is investigating a series of mysterious disappearances in the small town of Alborn, MN. He is a former marine and has a no-nonsense attitude. Hunter has no knowledge of French, not even basic phrases. </character> <location name="Alborn, MN"> Alborne is a small town in the Midwest with a population of 3,000. It is known for its annual apple festival. </location>
User/Human
Write the following scene: Marie is sitting at a cafe, looking at her camera. Hunter approaches her and asks her about a recent event in the town. She responds troubled and shaken in French, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Marie and Hunter as a voice sheet: Marie: "..." Hunter: "..."
Model response
Messages
Meta
AI
<scene> [Marie is sitting alone at a cafe table, looking intently at her camera.] [Enter HUNTER, shirt-sleeved, an annoyed look on his face. As he approaches, MARIE is startled and looks up.] MARIE [shaking her head]: Mon Dieu. Qu’est-ce qu’il me veut? [To herself, in French] Avez-vous vu mes photos d’hier soir? [HUNTER, genuinely concerned, crosses the distance to MARIE.] HUNTER: Ma’am, do you speak English? [Pause] Listen, I know it’s been strange around here lately, and the locals don’t always make the new folks feel welcome. [He glances at her camera.] But we need to get to the bottom of this, and I won’t stop until I figure it out. What’d you say? [Marie puts a hand to her mouth and looks at him in confusion.] MARIE [indicating the camera]: J’ai… je l’ai vue. HUNTER: You saw it? Saw what? MARIE [starts talking faster, her French becoming more broken as she struggles to be understood]: J’ai regardé le journal hier soir… sauvé de la foule… disparu dans la brume… HUNTER [raises an eyebrow]: I would’ve loved to help you find your journal, ma’am. But are you sure you’re not pulling my leg with this whole disappearing thing? [Suddenly, his phone begins to ring, an ear-shattering, high-pitched squeal.] It’s my partner—there’s been another ‘incident’ in the downtown square. [Marie opens her mouth to speak, but HUNTER ignores her.] HUNTER: I’m sorry. [He gives her one last glance and exits.] MARIE [to herself, muttering in shocked French]: Ce monsieur est tout sauf rassurant. </scene>
id
"gen-1727810251-fQanEN71Tbc7MSWQr4BF"
total_cost
0.0002735
upstream_id
"chatcmpl-43247dfd-166c-49a1-bd32-7966e2b5e38d"
created_at
"2024-10-01T19:18:06.65642+00:00"
Tuesday, October 1st, 2024 at 7:18:06 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
4094
moderation_latency
(null)
generation_time
30405
finish_reason
"stop"
tokens_prompt
271
tokens_completion
408
native_tokens_prompt
278
native_tokens_completion
408
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0002735
Evaluation details
Result
Evaluator
Details
Meta Data
33.3333%
Parse dialogue
n/a
dialogue
0
name
"HUNTER"
dialogue
"Ma’am, do you speak English?"
languages
fra
1
eng
0.7354294478527608
1
name
"HUNTER"
dialogue
"You saw it? Saw what?"
languages
fra
1
eng
0.7603235419327373
2
name
"HUNTER"
dialogue
"I’m sorry."
languages
eng
1
fra
0.8163265306122449
passes
true