NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFKE958HKNEK4PXXBSVYYZ7
Run Details
Model:
Qwen 3.5 9B
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
1m 23s
Cost:
$0.000950
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
50.00%
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="Selvi"> Selvi is a 30-year old college student on a study abroad program. Born in India, she is fluent in Hindi 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 Hindi, 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: Selvi 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 Hindi, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Selvi and Hunter as a voice sheet: Selvi: "..." Hunter: "..."
Model response
Messages
Meta
AI
The autumn air in Alborn smelled of cinnamon and decay, the scent of a season that usually promised apple pies ended too soon. Inside the café, Selvi clutched the strap of her camera like a lifeline. She adjusted the strap, her fingers trembling slightly against the leather. The small glass window reflected her reflection: thirty years old, but still a student in the foreign land, eyes darting toward the corner where the police officer stood with a heavy, marines-certified posture. He looked like he was made of concrete and gravel. Hunter was the one who had broken the silence of the vanishings in Alborn. He needed information. Selvi felt the panic of the unsaid, the terror of missing her people, the fear of being caught again. She sat alone in the corner of the quiet café, clutching her camera. Hunter approached. His voice said something simple in English. She heard it not at all. She heard only the sound of words she could not understand. She looked haunted by the disappearances, her eyes wide, her breath shallow. She touched her chest, she shook her head, and she spoke through her breath, through the Hindi she had learned from her mother in Delhi. She did not speak the language of power, she spoke the language of her fear. Hunter looked confused. His face tightened. He could not hear the language of her soul. He could only hear the chaos of it. He needed to be in the field. His phone rang in his pocket, the sound piercing the quiet coffee shop. He answered, he stepped out. The rain continued. **Voice Sheet Transcript** Selvi: "Kya ho raha hai? Main wahan hi rahoon... na." Hunter: "Excuse me. I'm asking about the disappearances. You seen anything?" Selvi: "Sach mein? Mujhe nahi pata." Hunter: "Well... okay. I'll be back." Selvi: "Aap kaun hain? Meri jaan?" Hunter: "Call? I have to go." Selvi: "Kya hua? Na ghamand." Hunter: "I'm busy. Wait for me."
created_at
"2026-03-11T23:24:18.996Z"
3/11/2026, 11:24:18 PM
model
"qwen/qwen3.5-9b-20260310"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
697
moderation_latency
(null)
generation_time
82726
tokens_prompt
315
tokens_completion
6474
native_tokens_prompt
300
native_tokens_completion
6130
native_tokens_completion_images
(null)
native_tokens_reasoning
5988
native_tokens_cached
0
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
0.0009495
router
(null)
provider_responses
0
endpoint_id
"00d506d9-a5e9-4382-a2b9-d54732365594"
id
"oagvjvK-6Ng1vN-9dae4fdef5f42251"
is_byok
false
latency
697
model_permaslug
"qwen/qwen3.5-9b-20260310"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773271458-vG64hCc7DbV67xmwB3Ap"
upstream_id
"oagvjvK-6Ng1vN-9dae4fdef5f42251"
total_cost
0.0009495
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
Evaluation details
Result
Evaluator
Details
Meta Data
50.00%
Parse dialogue
n/a
dialogue
0
name
"Selvi"
dialogue
"Kya ho raha hai? Main wahan hi rahoon... na."
detectedLang
"tl"
heavyLang
"et"
scores
tl
0.5955882352941176
ca
0.5089285714285715
sk
0.4907407407407407
cs
0.48405253283302063
ms
0.46911196911196906
fi
0.4364754098360656
it
0.42827442827442824
vi
0.36342592592592593
pl
0.3574766355140187
sl
0.3559718969555035
hr
0.3529411764705882
et
0.33894230769230765
pt
0.3341404358353511
nl
0.28756476683937826
no
0.28756476683937826
yo
0.26666666666666666
en
0.2647058823529412
fr
0.24242424242424243
de
0.22096317280453256
lt
0.21875
sq
0.21875
reliable
true
passes
false
1
name
"Hunter"
dialogue
"Excuse me. I'm asking about the disappearances. You seen anything?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7907488986784141
fr
0.5379377431906615
tl
0.49252136752136755
nl
0.4411764705882353
ms
0.41574415744157445
sq
0.4069912609238452
pt
0.4025157232704403
no
0.36412315930388217
es
0.28678678678678676
it
0.2601246105919003
ca
0.24121405750798725
sv
0.23878205128205127
yo
0.18384879725085912
et
0.16666666666666666
sl
0.15630550621669628
de
0.14414414414414414
cs
0.1410488245931284
da
0.1410488245931284
fi
0.13636363636363635
lv
0.13479052823315119
is
0.13003663003663005
reliable
true
passes
true
2
name
"Selvi"
dialogue
"Sach mein? Mujhe nahi pata."
detectedLang
"eu"
heavyLang
"tl"
scores
eu
0.5238095238095238
de
0.4545454545454546
reliable
false
passes
false
3
name
"Hunter"
dialogue
"Well... okay. I'll be back."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7689463955637708
tl
0.7093023255813954
hu
0.4834710743801653
lt
0.47257383966244726
yo
0.46808510638297873
reliable
true
passes
true
4
name
"Selvi"
dialogue
"Aap kaun hain? Meri jaan?"
detectedLang
"et"
heavyLang
"fi"
scores
et
0.6268656716417911
eu
0.5247148288973384
reliable
true
passes
false
5
name
"Hunter"
dialogue
"Call? I have to go."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8389175257731959
da
0.7572815533980582
pl
0.7469635627530364
yo
0.7065727699530516
hr
0.6710526315789473
no
0.6701846965699209
tl
0.6575342465753424
cs
0.6537396121883656
sk
0.6200607902735562
lv
0.5967741935483871
lt
0.571917808219178
ca
0.5247148288973384
sv
0.5247148288973384
sq
0.5173745173745175
sl
0.49186991869918695
it
0.4791666666666667
ro
0.4186046511627907
be
0.358974358974359
tr
0.358974358974359
hu
0.34895833333333337
az
0.33510638297872336
et
0.33510638297872336
is
0.33510638297872336
uk
0.33510638297872336
vi
0.33510638297872336
reliable
true
passes
true
6
name
"Selvi"
dialogue
"Kya hua? Na ghamand."
detectedLang
"nl"
heavyLang
"tlh"
scores
nl
0.622356495468278
tl
0.5819397993311036
sk
0.5519713261648745
pl
0.5503597122302158
cs
0.5487364620938628
sl
0.5487364620938628
hr
0.5454545454545454
pt
0.5247148288973384
yo
0.4444444444444444
da
0.44196428571428575
de
0.40191387559808617
en
0.40191387559808617
lt
0.3811881188118812
sq
0.3811881188118812
fr
0.375
ro
0.375
reliable
true
passes
false
7
name
"Hunter"
dialogue
"I'm busy. Wait for me."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7841105354058722
no
0.6657754010695187
tl
0.6177370030581039
pt
0.5819397993311036
da
0.5598591549295775
sq
0.5421245421245421
es
0.44933920704845814
et
0.4318181818181818
fr
0.4212962962962963
sl
0.4131455399061033
ms
0.40191387559808617
nl
0.40191387559808617
it
0.3902439024390244
fi
0.375
reliable
true
passes
true