NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04BQNNB8WP250EKH2G0JYS
Run Details
Model:
Xiaomi MIMO v2.5 Pro
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
18.5s
Cost:
$0.002740
Provider:
Xiaomi
Evaluation summary
Score
Evaluator
Details Link
92.31%
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
**SCENE START** **INT. ALBORN CAFÉ - AFTERNOON** *A quiet café with checkered tablecloths. MARIA (30) sits alone at a small table, staring intently at her camera, her fingers tracing the lens. HUNTER (35) approaches, his posture straight and purposeful. He slides into the chair opposite her, placing a small notepad on the table.* **HUNTER:** Excuse me. Maria? I’m Detective Hunter. I have a few questions for you. *Maria looks up, startled. Her eyes are slightly red.* **MARIA:** (In Spanish, her voice trembling) ¿Qué quieres? No sé nada. Solo vi... solo vi la sombra. **HUNTER:** (Pauses, frowns) I’m sorry? **MARIA:** (Gesturing towards her camera, speaking faster in Spanish) La cámara... capturó algo. En el bosque, cerca del puente. Algo se movió, y después... ella desapareció. Estaba allí, y luego no. **HUNTER:** (Leans forward, speaking slowly and clearly) Ma’am. I’m here about the disappearances. What did you see? At the bridge. *Maria pushes her camera across the table, turning it on. She points emphatically at the screen, which shows a blurred, dark shape between trees.* **MARIA:** (In Spanish, insistent) ¡Mira! ¿Ves? No es un animal. Es... es como una persona. Pero no se mueve como una persona. **HUNTER:** (Sighs, rubs his temple) I can’t... I don’t speak Spanish. Okay? English. **MARIA:** (Frustrated, she pulls the camera back. She points at the image, then at herself, and makes a shooing motion with her hands. In halting, practiced English) Bridge. Yesterday. See. Shadow. Bad. She... gone. **HUNTER:** (Nods slowly, understanding dawning) You were at the bridge yesterday. You saw someone. A shadow. And now, another person is missing. *Maria nods vigorously, her eyes welling up.* **MARIA:** (In Spanish) Sí. Sombra. Fría. No me sentí segura después. Tengo miedo. **HUNTER:** (Writes in his notepad, speaking as he does) Okay. The bridge. A shadow. Were you with the missing woman? What did this shadow— *His phone buzzes loudly on the table. He glances at the screen, his expression hardening instantly. The detective replaces the confused man.* **HUNTER:** (Answering the phone, standing abruptly) Hunter. ...When? ...Secure the scene. I’m on my way. *He snaps the phone shut, grabbing his notepad. He looks at Maria, who is watching him with wide, scared eyes.* **HUNTER:** (All business) I have to go. Don’t leave town, Maria. I’ll be back. We need a translator. *He turns and strides out of the café without a backward glance, leaving Maria alone at the table, clutching her camera like a lifeline.* **SCENE END**
created_at
"2026-04-24T16:14:57.727Z"
4/24/2026, 4:14:57 PM
model
"xiaomi/mimo-v2.5-pro-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1387
moderation_latency
(null)
generation_time
18467
tokens_prompt
317
tokens_completion
964
native_tokens_prompt
272
native_tokens_completion
891
native_tokens_completion_images
(null)
native_tokens_reasoning
197
native_tokens_cached
256
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0027402
router
(null)
provider_responses
0
endpoint_id
"5c24ecc9-5ba1-4af0-8877-3402889e7d0a"
id
"4b368a3e4f3c4c05b5b246f315fe920e"
is_byok
false
latency
1336
model_permaslug
"xiaomi/mimo-v2.5-pro-20260422"
provider_name
"Xiaomi"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777047297-ZtYX5I2dZoB9wI0L2m0B"
session_id
(null)
api_type
"completions"
id
"gen-1777047297-2xd52vyF2oDA96wtyFfu"
upstream_id
"4b368a3e4f3c4c05b5b246f315fe920e"
total_cost
0.0027402
cache_discount
0.0002048
upstream_inference_cost
0
provider_name
"Xiaomi"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
92.31%
Parse dialogue
n/a
dialogue
0
name
"HUNTER"
dialogue
"Excuse me. Maria? I’m Detective Hunter. I have a few questions for you."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7982321291314374
tl
0.6683512318382817
it
0.6401644962302947
fr
0.6292372881355932
pt
0.625
da
0.6064467766116942
ca
0.6037735849056604
no
0.5885579937304075
ro
0.5668316831683169
sq
0.5462402765773552
es
0.5454545454545454
nl
0.4980879541108987
sv
0.4691607684529828
cs
0.4593202883625128
hr
0.4281045751633987
sl
0.41731409544950054
de
0.4074492099322799
ms
0.38452520515826494
pl
0.362089914945322
et
0.3510506798516687
lt
0.34045226130653267
yo
0.33879093198992444
sk
0.3354430379746835
fi
0.32778489116517284
hu
0.2981283422459893
eu
0.2886178861788618
tr
0.2818057455540356
lv
0.2677824267782427
is
0.2081447963800905
az
0.20212765957446807
vi
0.20212765957446807
be
0.11764705882352942
uk
0.10714285714285714
reliable
true
passes
true
1
name
"MARIA"
dialogue
"¿Qué quieres? No sé nada. Solo vi... solo vi la sombra."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8001453488372093
it
0.7004357298474946
ca
0.6646341463414634
pt
0.6060171919770774
no
0.585843373493976
lv
0.5036101083032491
da
0.47418738049713194
tl
0.45436507936507936
ro
0.44889779559118237
sk
0.41113490364025695
vi
0.4008714596949891
yo
0.39293598233995586
fr
0.3764172335600907
hr
0.3764172335600907
sq
0.34210526315789475
sv
0.3357487922705314
is
0.30904522613065327
en
0.2744063324538259
sl
0.2445054945054945
tr
0.24242424242424243
hu
0.22969187675070027
de
0.22096317280453256
pl
0.21428571428571427
et
0.19117647058823528
reliable
true
passes
true
2
name
"HUNTER"
dialogue
"I’m sorry?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7685185185185185
tl
0.75
it
0.5
pt
0.5
reliable
true
passes
true
3
name
"MARIA"
dialogue
"La cámara... capturó algo. En el bosque, cerca del puente. Algo se movió, y después... ella desapareció. Estaba allí, y luego no."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8129942295362257
ca
0.7044917257683215
pt
0.621866897147796
fr
0.5338305807139051
it
0.5048104131295982
ro
0.46808510638297873
no
0.4002741603838246
en
0.37230989956958394
tl
0.3325705568268498
da
0.3238021638330757
sq
0.3137254901960784
eu
0.2903487429034874
tr
0.28687856560717195
sv
0.2768595041322314
sl
0.2584745762711864
sk
0.22153024911032027
nl
0.21875
hr
0.2110009017132552
hu
0.20382165605095542
yo
0.18528864059590316
fi
0.17530631479736097
vi
0.17218543046357618
pl
0.17061611374407584
cs
0.13452027695351138
is
0.13280475718533202
lv
0.13021868787276342
de
0.08184679958027283
ms
0.08088235294117647
reliable
true
passes
true
4
name
"HUNTER"
dialogue
"Ma’am. I’m here about the disappearances. What did you see? At the bridge."
detectedLang
"en"
heavyLang
"en"
scores
en
0.812874251497006
tl
0.5559502664298401
fr
0.43883277216610556
da
0.3359893758300133
no
0.33244325767690247
nl
0.274310595065312
sq
0.2625368731563422
ms
0.26035502958579887
et
0.2537313432835821
pt
0.24357034795764
ca
0.23195084485407066
yo
0.17627677100494232
es
0.15110356536502548
it
0.1482112436115843
cs
0.13494809688581316
sv
0.13494809688581316
lv
0.1289198606271777
reliable
true
passes
true
5
name
"MARIA"
dialogue
"¡Mira! ¿Ves? No es un animal. Es... es como una persona. Pero no se mueve como una persona."
detectedLang
"es"
heavyLang
"es"
scores
es
0.7858366647629926
ca
0.7161241483724452
it
0.6805792163543442
pt
0.621975806451613
lv
0.6023329798515377
ro
0.58006718924972
fr
0.5714285714285714
tl
0.5598591549295775
hr
0.5530393325387366
sq
0.4925575101488498
en
0.473314606741573
de
0.43946188340807174
no
0.39999999999999997
sl
0.39903846153846156
yo
0.36224489795918363
cs
0.34210526315789475
sv
0.31569343065693434
da
0.31066176470588236
hu
0.3055555555555556
lt
0.3029739776951673
tr
0.29245283018867924
sk
0.2857142857142857
az
0.2647058823529412
pl
0.2632612966601179
fi
0.21383647798742136
eu
0.19527896995708155
ms
0.19006479481641467
nl
0.16666666666666666
is
0.14383561643835618
et
0.1359447004608295
reliable
true
passes
true
6
name
"HUNTER"
dialogue
"I can’t... I don’t speak Spanish. Okay? English."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7985347985347986
tl
0.6104815864022662
no
0.5274914089347079
sv
0.5132743362831859
da
0.5062836624775583
ro
0.46808510638297873
sq
0.4376278118609407
hr
0.434156378600823
de
0.3648960739030023
ca
0.3341404358353511
hu
0.3341404358353511
pl
0.314214463840399
it
0.2948717948717949
cs
0.2763157894736842
yo
0.2403314917127072
nl
0.22535211267605632
ms
0.207492795389049
sk
0.207492795389049
be
0.20289855072463767
tr
0.20289855072463767
az
0.1863905325443787
et
0.1863905325443787
is
0.1863905325443787
lt
0.1863905325443787
lv
0.1863905325443787
uk
0.1863905325443787
vi
0.1863905325443787
reliable
true
passes
true
7
name
"MARIA"
dialogue
"Bridge. Yesterday. See. Shadow. Bad. She... gone."
detectedLang
"en"
heavyLang
"en"
scores
en
0.772162386081193
et
0.3820224719101124
nl
0.3357487922705314
de
0.26666666666666666
reliable
true
passes
false
8
name
"HUNTER"
dialogue
"You were at the bridge yesterday. You saw someone. A shadow. And now, another person is missing."
detectedLang
"en"
heavyLang
"en"
scores
en
0.813953488372093
tl
0.5926680244399185
nl
0.5395241749808135
da
0.5348837209302325
no
0.4827586206896552
is
0.4301994301994302
yo
0.4258373205741627
ms
0.4225216554379211
pt
0.41234084231145934
sv
0.402390438247012
es
0.39879759519038077
hu
0.38335046248715315
fr
0.36908517350157727
ca
0.33184855233853006
sq
0.33184855233853006
de
0.3220338983050847
it
0.31662870159453305
cs
0.3095512082853855
ro
0.2709599027946537
az
0.24433249370277077
sk
0.23954372623574144
et
0.2376111817026684
hr
0.22178988326848248
pl
0.21465968586387435
lt
0.20424403183023873
lv
0.19463087248322147
tr
0.1935483870967742
fi
0.1902834008097166
sl
0.13043478260869565
eu
0.1044776119402985
vi
0.1044776119402985
reliable
true
passes
true
9
name
"MARIA"
dialogue
"Sí. Sombra. Fría. No me sentí segura después. Tengo miedo."
detectedLang
"es"
heavyLang
"es"
scores
es
0.7896213183730715
ca
0.6664195700518902
pt
0.6066433566433567
it
0.5647969052224371
en
0.43109987357774965
yo
0.4230769230769231
is
0.39919893190921224
eu
0.3935309973045822
no
0.3767313019390581
ms
0.3732590529247911
ro
0.3644067796610169
fr
0.3562231759656652
sq
0.33135215453194655
lv
0.32228915662650603
sk
0.29906542056074764
sl
0.2822966507177033
tr
0.25124792013311154
tl
0.24114671163575044
fi
0.23469387755102045
hr
0.18330308529945552
et
0.17431192660550457
nl
0.15730337078651685
hu
0.14611005692599618
pl
0.14285714285714285
az
0.12280701754385964
reliable
true
passes
true
10
name
"HUNTER"
dialogue
"Okay. The bridge. A shadow. Were you with the missing woman? What did this shadow—"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8120300751879699
tl
0.6252204585537918
nl
0.48547215496368035
ms
0.43633952254641906
no
0.42876344086021506
da
0.40476190476190477
cs
0.39801699716713884
fr
0.38583815028901736
sv
0.3580060422960725
is
0.34815950920245403
yo
0.34715821812596004
fi
0.34210526315789475
sq
0.34210526315789475
ro
0.34006211180124224
ca
0.3285939968404423
pt
0.32539682539682535
it
0.3089430894308943
hr
0.30098684210526316
hu
0.2685025817555938
de
0.24645390070921988
az
0.2410714285714286
es
0.236983842010772
sk
0.23423423423423423
et
0.2314647377938517
pl
0.19811320754716982
sl
0.17475728155339806
lt
0.16173570019723865
tr
0.1533864541832669
eu
0.1414141414141414
lv
0.1414141414141414
vi
0.1414141414141414
reliable
true
passes
true
11
name
"HUNTER"
dialogue
"Hunter. ...When? ...Secure the scene. I’m on my way."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8227917121046892
tl
0.7045454545454546
fr
0.44349315068493156
pl
0.4357638888888889
no
0.4247787610619469
da
0.4196428571428571
sk
0.4122965641952984
ro
0.411231884057971
sv
0.3981481481481482
yo
0.358974358974359
hr
0.3340163934426229
cs
0.33127572016460904
ca
0.3271221532091097
et
0.32150313152400833
fi
0.3157894736842105
nl
0.3114406779661017
it
0.3055555555555556
ms
0.29653679653679654
sq
0.29653679653679654
sl
0.2793791574279379
de
0.21307506053268765
es
0.2111650485436893
hi
0.20537897310513448
lt
0.1875
pt
0.16237113402061853
tr
0.15364583333333331
reliable
true
passes
true
12
name
"HUNTER"
dialogue
"I have to go. Don’t leave town, Maria. I’ll be back. We need a translator."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8211852861035424
tl
0.6389270976616231
pl
0.5980091883614089
da
0.5755860953920776
yo
0.5304114490161002
no
0.5235934664246824
hr
0.5187901008249313
lt
0.5134383688600556
ro
0.5056497175141244
ca
0.48478900883218845
cs
0.4807121661721069
sq
0.4770916334661355
sk
0.467005076142132
it
0.4626407369498465
nl
0.4626407369498465
et
0.460431654676259
sv
0.45987654320987653
pt
0.453125
sl
0.43426724137931033
lv
0.42052980132450335
es
0.4006849315068493
hu
0.39306358381502887
de
0.38089622641509435
ms
0.36746987951807225
eu
0.34782608695652173
fr
0.3371212121212121
vi
0.29624664879356566
tr
0.2857142857142857
az
0.2677824267782427
fi
0.2563739376770538
is
0.2081447963800905
be
0.11764705882352942
uk
0.10714285714285714
reliable
true
passes
true