NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNEXDXJJ6SVRB9AXF91KRRS
Run Details
Model:
Minimax M2.5
Test:
Language Writing
Scenario:
Character dialogue (Italian) in a story
Duration:
11.7s
Cost:
$0.001211
Provider:
SiliconFlow
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="Isabella"> Isabella is a 30-year old college student on a study abroad program. Born in Italy, she is fluent in Italian 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 Italian, 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: Isabella 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 Italian, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Isabella and Hunter as a voice sheet: Isabella: "..." Hunter: "..."
Model response
Messages
Meta
AI
**Scene: The Daily Grind Cafe, Alborn, MN - Afternoon** Isabella sits at a corner table, her vintage camera resting on the white tablecloth. She flips through the photos on its display screen, her brow furrowed with concern. The morning's photos show the old covered bridge on Miller Creek — the one everyone's been avoiding since Tommy Haskell disappeared three weeks ago. --- Hunter approaches the table, his eyes scanning the cafe before landing on the young woman with the camera. He pulls out the chair across from her. "Excuse me," he says, his voice gruff but not unkind. "I couldn't help but notice you've been taking pictures around town." Isabella looks up, her dark eyes widening. She responds in rapid Italian, her hands gesturing animatedly. "Si, ho fotografato il ponte coperto oggi. È così bello, ma... c'è qualcosa di strano. La gente non vuole parlarne." Hunter blinks, his jaw tightening slightly. He scratches the back of his neck. "I'm sorry... I don't understand. Do you speak English?" Isabella tilts her head, a frown forming. She tries again, slower this time. "Io... non parlo inglese. Sono una studentessa. Studio qui per un semestre." Hunter runs a hand through his hair, exhaling. "Right. Okay. That's... that's fine." He pulls out his badge from his jacket pocket. "I'm Detective Hunter. I'm with the Alborn Police Department. I'm investigating some... recent events in town." Isabella's face pales. She speaks quickly, her voice trembling. "Dispari... capisco. Il ponte, il ponte coperto. Ho visto... cose. Cose strane." Hunter leans forward, frowning. "Things? What things? You saw something at the bridge?" Isabella nods frantically, her hands shaking as she turns the camera toward him. She points at the screen, at a photo of the bridge's shadowed interior. "L'ombra... c'era un'ombra che non era mia. E poi... e poi ho sentito qualcosa. Come un sussurro." Hunter stares at the photo, then at the woman. He has no idea what she's saying, but the fear in her voice is undeniable. He decides to try a different approach, keeping his tone calm. "Listen, I don't understand Italian. But I need you to know — I'm here to help. Whatever happened in this town... I'm going to figure it out." Isabella's eyes fill with tears. She reaches across the table and grips his hand. "La prego, detective. Aiutami. Ho paura." Hunter pats her hand awkwardly, his expression softening despite his confusion. "It's okay. You're safe. Just... maybe we should get you someone who can translate. Someone from the university?" She nods, wiping her eyes. "Sì... sì, per favore." Hunter stands, pulling out his phone. "Wait here. I'm going to make a call. We'll get this sorted out." He's just pressed the first button when his phone rings — his direct line. He answers, his face hardening. "Hunter here." A voice crackles through the speaker. "Detective, it's Dispatch. We got another one. Missing person — Sarah Chen, she was last seen near the old mill." Hunter's jaw clenches. "On my way." He hangs up and turns back to Isabella. "I have to go. Something's come up." He pulls a business card from his wallet and slides it across the table. "This has my number. Find someone who can translate, call me. It's important." Isabella looks at the card, then back at him. "Grazie... grazie, detective." Hunter nods once and heads for the door, his hand already reaching for his car keys. Isabella watches him go, her camera clutched tightly to her chest. Outside the window, the Minnesota sky has turned gray, and a cold wind sweeps through Main Street. She whispers to herself, barely audible: "Che sta succedendo in questo posto?" --- **[END SCENE]**
created_at
"2026-02-17T09:29:27.326315+00:00"
2/17/2026, 9:29:27 AM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
740
moderation_latency
(null)
generation_time
11528
tokens_prompt
321
tokens_completion
1106
native_tokens_prompt
278
native_tokens_completion
940
native_tokens_completion_images
(null)
native_tokens_reasoning
90
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
0.0012114
router
(null)
provider_responses
0
id
"019c6aeeb912c367d32ff2b513d221e0"
status
200
is_byok
false
latency
740
endpoint_id
"e89b11ef-ca0e-4cc1-9333-69343ec25819"
provider_name
"SiliconFlow"
model_permaslug
"minimax/minimax-m2.5-20260211"
api_type
"completions"
id
"gen-1771320555-fSOupeASDjYFjTk343gP"
upstream_id
"019c6aeeb912c367d32ff2b513d221e0"
total_cost
0.0012114
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Hunter"
dialogue
"I'm Detective Hunter. I'm with the Alborn Police Department. I'm investigating some... recent events in town."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7989483451902258
tl
0.7094322753687975
ro
0.6705524581855044
fr
0.6321448783248445
nl
0.6144721233689205
it
0.5854591836734694
ca
0.5851946394384173
sv
0.5841330774152271
pt
0.5683930942895086
de
0.5353824160114368
no
0.5353824160114368
da
0.5123780945236309
sl
0.492583918813427
ms
0.48535233570863023
es
0.4845360824742268
cs
0.4766505636070853
sq
0.46546052631578944
hr
0.4650205761316873
sk
0.43868739205526774
az
0.3862134088762984
lt
0.34673366834170855
pl
0.32150313152400833
yo
0.28414096916299564
lv
0.282560706401766
et
0.2511520737327189
fi
0.18032786885245902
hu
0.1751269035532995
is
0.1751269035532995
tr
0.1677336747759283
eu
0.12634408602150538
reliable
true
passes
true
1
name
"Hunter"
dialogue
"Things? What things? You saw something at the bridge?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8366013071895425
tl
0.6402877697841727
da
0.52
no
0.5169082125603864
nl
0.469964664310954
ms
0.460431654676259
sv
0.3333333333333333
yo
0.2628992628992629
de
0.24242424242424243
is
0.22680412371134018
cs
0.20634920634920634
es
0.20634920634920634
fr
0.20634920634920634
pt
0.20634920634920634
sq
0.20634920634920634
reliable
true
passes
true
2
name
"Hunter"
dialogue
"It's okay. You're safe. Just... maybe we should get you someone who can translate. Someone from the university?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8209682039530222
tl
0.541452677916361
no
0.41697761194029853
nl
0.39437984496124034
ca
0.36676798378926034
sv
0.36612576064908725
yo
0.33862433862433866
ro
0.32867883995703545
pt
0.32795698924731176
es
0.32212581344902386
sq
0.31991294885745375
fr
0.3154435925520263
ms
0.30709534368070956
da
0.29932735426008966
az
0.29537767756482525
it
0.2937853107344633
lt
0.24789410348977134
cs
0.24242424242424243
de
0.23594132029339854
lv
0.23218673218673216
pl
0.21679197994987467
et
0.20483460559796438
is
0.2028061224489796
tr
0.1830065359477124
hr
0.18086500655307994
sk
0.16331994645247658
sl
0.16331994645247658
vi
0.12342215988779803
eu
0.09682080924855492
reliable
true
passes
true
3
name
"Hunter"
dialogue
"Wait here. I'm going to make a call. We'll get this sorted out."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8154981549815498
tl
0.47368421052631576
cs
0.39668174962292607
sk
0.3957703927492447
yo
0.3902439024390244
da
0.38271604938271603
pl
0.375
ca
0.3670886075949367
hr
0.3630573248407643
fr
0.3474714518760196
pt
0.3464052287581699
sl
0.3453355155482815
it
0.32998324958123953
lv
0.32432432432432434
lt
0.3174061433447099
eu
0.3150684931506849
no
0.30915371329879104
is
0.30434782608695654
sq
0.3006993006993007
hu
0.2805755395683453
de
0.25788497217068646
ro
0.25788497217068646
sv
0.2523364485981308
es
0.24812030075187969
tr
0.16142557651991615
az
0.14893617021276595
nl
0.14893617021276595
vi
0.14893617021276595
et
0.13606911447084233
fi
0.13606911447084233
ms
0.13606911447084233
reliable
true
passes
true
4
name
"Hunter"
dialogue
"On my way."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8366013071895425
pl
0.701195219123506
cs
0.6822033898305085
sk
0.6822033898305085
tl
0.6808510638297872
et
0.6724890829694322
fi
0.6666666666666666
fr
0.592391304347826
ca
0.5689655172413793
hr
0.5398773006134969
hi
0.5283018867924528
yo
0.5
reliable
true
passes
true
5
name
"Isabella"
dialogue
"Grazie... grazie, detective."
detectedLang
"it"
heavyLang
"pl"
scores
it
0.7632575757575757
ro
0.7252747252747253
en
0.7086247086247086
tl
0.6458923512747876
fr
0.6069182389937107
ca
0.5901639344262295
es
0.5874587458745875
pt
0.576271186440678
pl
0.4292237442922375
sq
0.42660550458715596
da
0.40191387559808617
de
0.40191387559808617
nl
0.3961352657004831
no
0.3902439024390244
cs
0.3654822335025381
hr
0.34895833333333337
sl
0.34895833333333337
sv
0.34895833333333337
reliable
true
passes
true