NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7YMDV8H55XJW9KP1QZ4FG
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
9.6s
Cost:
$0.000106
Provider:
WandB
Evaluation summary
Score
Evaluator
Details Link
100.00%
Parse dialogue
(details)
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="Maria"> Maria is a 30-year old college student on a study abroad program. Born in Spain, she is fluent in Spanish 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 Spanish, 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: Maria 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 Spanish, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Maria and Hunter as a voice sheet: Maria: "..." Hunter: "..."
Model response
Messages
Meta
AI
**Voice Sheet – "Lost in Translation"** *[Scene: A quiet corner of Maple & Bean Café in Alborn, MN. Autumn light filters through the windows. MARIA, 30, sits at a small table, staring at her camera screen, her hands slightly trembling. She zooms in on a blurry photo of the town square at dusk. HUNTER, 35, in a worn leather jacket and stern expression, approaches.]* **Hunter:** You the one been taking pictures around town? Saw you near the old mill yesterday. *Maria looks up, startled. She fumbles her camera and blinks rapidly, clearly distressed.* **Maria:** ¡Dios mío... no sé qué vi! ¡Era un hombre, pero... no podía verle la cara! Solo sombra… y el silencio. Y luego... desapareció. Como si el bosque lo hubiera tragado. ¡Tenéis que hacer algo! *Hunter blinks, brow furrowing. He tilts his head slightly, unable to understand.* **Hunter:** I... uh... sorry. I don’t speak Spanish. You okay, miss? *Maria takes a breath, realizing he doesn’t understand. She points vigorously at her photo, then gestures toward the woods beyond town.* **Maria:** ¡Allí! ¡En el bosque! ¡Vi algo anoche! ¡No era normal! ¡Y la luz en la foto... no estaba cuando tomé la imagen! *She traces a glowing orb in the image with her finger, eyes wide. Hunter leans in, studying the photo. He frowns, intrigued despite the language barrier.* **Hunter:** You saw something in the woods? At night? *She nods urgently, speaking quickly.* **Maria:** ¡Sí! ¡A eso de las once! Estaba fotografiando el atardecer... y de repente, todo se oscureció. Escuché un sonido... como un susurro. Y luego... nada. Silencio total. *Hunter pulls out his notepad, scribbling: "Spanish speaker – saw anomaly near woods ~9 PM? Possible witness." He looks at her, softening slightly.* **Hunter:** You were alone? *Maria nods, shivering. She hugs her camera close.* **Maria:** Estoy sola aquí. No hablo bien... no entiendo a nadie. Pero esto no es normal. Algo le pasa a esta ciudad. *Hunter rubs his jaw, conflicted. Before he can respond, his phone vibrates sharply. He answers.* **Hunter:** Yeah. Hunter here. *[Pause. His expression tightens.]* **Hunter:** Another one missing? Where? [Beat, then sharper:] Same trail near Black Pine Ridge? [Long pause.] I’m on my way. *He hangs up, sighs, and looks back at Maria with reluctant urgency.* **Hunter:** I gotta go. But... stay out of the woods. Stay safe, okay? *Maria stares at him, sensing the gravity. She speaks softly, almost pleading.* **Maria:** Por favor... investiga la iglesia vieja. La que está entre los árboles. Nadie la menciona... pero está en mis fotos. Siempre está allí. *Hunter hesitates, then nods slowly—not understanding the words, but reading the fear in her eyes.* **Hunter:** Alright. I’ll check it out. Thanks for... whatever it is you’re trying to tell me. *He turns and walks out. Maria watches him go, then looks down at her camera. The image on the screen flickers—just for a second—the faint outline of a crumbling church where none had been before.*
created_at
"2026-03-25T10:16:57.026Z"
3/25/2026, 10:16:57 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
146
moderation_latency
(null)
generation_time
9496
tokens_prompt
317
tokens_completion
845
native_tokens_prompt
274
native_tokens_completion
787
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
32
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0001061
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-8cd647fc249dce8c"
is_byok
false
latency
40
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"WandB"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774433817-xuWbGhApra4eDjwj2gqi"
upstream_id
"chatcmpl-8cd647fc249dce8c"
total_cost
0.0001061
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Hunter"
dialogue
"Spanish speaker – saw anomaly near woods ~9 PM? Possible witness."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7659449970743125
tl
0.5689655172413793
ca
0.50186799501868
fr
0.42857142857142855
pt
0.3220338983050847
ms
0.3055555555555556
nl
0.29328621908127206
no
0.29328621908127206
sv
0.29328621908127206
de
0.28698752228163993
da
0.2673992673992674
it
0.2277992277992278
es
0.20634920634920634
hi
0.18699186991869918
ro
0.16666666666666666
sq
0.16666666666666666
cs
0.15789473684210525
lv
0.15789473684210525
hu
0.15074309978768577
reliable
true
passes
true