NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-25-01M3CKGR2D4ZEZFB2XXKF1REBY
Run Details
Model:
Mistral Medium 3.5 (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
4.1s
Cost:
$0.004052
Provider:
Mistral
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
Here’s the dialogue formatted as a voice sheet, capturing the tension and language barrier between Maria and Hunter: --- **Maria:** *(murmuring to herself, examining her camera)* "No puede ser... esto no tiene sentido..." *(This can't be... this doesn't make sense...)* **Hunter:** *(approaches, clearing his throat)* "Excuse me, miss. I’m Detective Hunter. Mind if I ask you a few questions about what happened at the festival last night?" **Maria:** *(startled, clutching her camera tighter, speaking rapidly in Spanish)* "¡Yo no sé nada! Solo estaba tomando fotos... no vi nada extraño, pero... pero algo no está bien aquí." *(I don’t know anything! I was just taking photos... I didn’t see anything strange, but... but something isn’t right here.)* **Hunter:** *(frowning, rubbing his temple)* "Uh... look, I don’t speak Spanish. You’re gonna have to slow down and—" **Maria:** *(gesturing frantically, mixing words with hand motions)* "¡Desaparecieron! La gente... se fueron, como fantasmas!" *(They disappeared! The people... they vanished, like ghosts!)* **Hunter:** *(sighs, pulling out a notepad)* "Okay, okay. Let’s try this—point to where it happened. Or... or draw it if you have to." **Maria:** *(hesitant, then sketches a quick map on a napkin, muttering)* "Aquí... cerca del viejo granero. Escuché gritos." *(Here... near the old barn. I heard screams.)* **Hunter:** *(studying the napkin, then looking up as his phone rings)* "Hell—excuse me." *(answers call)* "Hunter here... yeah, I’ll be right there." *(to Maria, apologetic)* "Look, I gotta go. But stay in town, alright? We’ll figure this out." **Maria:** *(nodding, still shaken)* "Lo intentaré... pero tenga cuidado." *(I’ll try... but be careful.)* **Hunter:** *(already walking away, confused but determined)* "Yeah. You too." --- This keeps the cozy mystery tone while highlighting the language barrier and the eerie undertones of the disappearances.
created_at
"2026-09-25T15:39:05.684Z"
9/25/2026, 3:39:05 PM
model
"mistralai/mistral-medium-3.5-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
388
moderation_latency
(null)
generation_time
4084
tokens_prompt
304
tokens_completion
505
native_tokens_prompt
281
native_tokens_completion
484
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
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"
service_tier
"default"
usage
0.0040515
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790350745-v0TFW3R1tPnzw1TpaAfi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790350745-j0mPXNTue76iQIrfKgv1"
upstream_id
"d569c5c372f7494387c54bcb0a0964c9"
provider_responses
0
endpoint_id
"d21d316f-d540-4718-b36e-3beff85d0cf9"
id
"d569c5c372f7494387c54bcb0a0964c9"
is_byok
false
latency
387
model_permaslug
"mistralai/mistral-medium-3.5-20260430"
provider_name
"Mistral"
status
200
total_cost
0.0040515
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Maria"
dialogue
"No puede ser... esto no tiene sentido..."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8344370860927153
pt
0.6676514032496307
no
0.6173469387755102
ca
0.608695652173913
it
0.6059544658493871
tl
0.4955156950672646
en
0.4260204081632653
tr
0.4015957446808511
fr
0.3935309973045822
ro
0.3835616438356164
fi
0.3818681318681319
lv
0.3679775280898876
hr
0.3098159509202454
da
0.3055555555555556
sv
0.3055555555555556
sk
0.2879746835443038
nl
0.27652733118971057
eu
0.27184466019417475
ms
0.267100977198697
pl
0.25
az
0.21875
reliable
true
passes
true
1
name
"Hunter"
dialogue
"Excuse me, miss. I’m Detective Hunter. Mind if I ask you a few questions about what happened at the festival last night?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8105650573717254
tl
0.6686861037485801
fr
0.568327577701036
it
0.5290635091496232
no
0.5267712276906436
da
0.5045300113250283
ca
0.4959677419354839
pt
0.4886031560490941
nl
0.45987654320987653
sq
0.44933920704845814
es
0.43402328589909445
ro
0.4292237442922375
sv
0.4201457919151756
cs
0.3961352657004831
hr
0.37230989956958394
et
0.3673174258857556
sl
0.35944363103953153
ms
0.3460388639760837
yo
0.30665610142630745
de
0.3044515103338633
hu
0.30167597765363136
sk
0.2677824267782427
pl
0.251497005988024
lt
0.23647469458987785
az
0.22291296625222026
tr
0.19056429232192415
fi
0.18680297397769516
lv
0.1830065359477124
is
0.1362290227048371
vi
0.13194444444444445
be
0.07407407407407407
eu
0.07407407407407407
uk
0.06716417910447761
reliable
true
passes
true
2
name
"Maria"
dialogue
"¡Yo no sé nada! Solo estaba tomando fotos... no vi nada extraño, pero... pero algo no está bien aquí."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8156836461126006
pt
0.6873223422399091
ca
0.6250852079072937
it
0.5175438596491229
tl
0.4675701839303001
sv
0.39293598233995586
en
0.38820912124582874
sk
0.36194895591647336
fr
0.35672514619883045
no
0.33894230769230765
lv
0.3251533742331288
pl
0.2912371134020619
cs
0.28848641655886154
nl
0.2819843342036553
de
0.27726675427069647
da
0.26764314247669774
yo
0.24657534246575344
hr
0.233983286908078
tr
0.2231638418079096
lt
0.20634920634920634
ro
0.2040520984081042
is
0.18276374442793464
eu
0.17043740573152338
vi
0.15384615384615385
sl
0.1085899513776337
et
0.10277324632952692
sq
0.10277324632952692
az
0.09688013136288999
reliable
true
passes
true
3
name
"Hunter"
dialogue
"Uh... look, I don’t speak Spanish. You’re gonna have to slow down and—"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7983870967741935
tl
0.5249999999999999
da
0.49252136752136755
no
0.4128553770086526
yo
0.40476190476190477
pl
0.3546195652173913
hr
0.3493150684931507
cs
0.3319268635724332
sv
0.31457431457431456
sq
0.31059506531204645
it
0.3055555555555556
sk
0.3004418262150221
lv
0.2803030303030303
et
0.27811550151975684
ro
0.26356589147286824
lt
0.2601246105919003
ca
0.22512234910277326
hu
0.22512234910277326
sl
0.2030201342281879
fi
0.19491525423728812
de
0.1532976827094474
nl
0.14414414414414414
be
0.12844036697247707
tr
0.12844036697247707
az
0.1171003717472119
is
0.1171003717472119
uk
0.1171003717472119
vi
0.1171003717472119
reliable
true
passes
true
4
name
"Maria"
dialogue
"¡Desaparecieron! La gente... se fueron, como fantasmas!"
detectedLang
"es"
heavyLang
"es"
scores
es
0.8054474708171206
pt
0.6956521739130436
it
0.6388028895768834
fr
0.5558375634517766
ca
0.5552731893265566
sq
0.5448634590377113
ro
0.5172413793103449
da
0.4791666666666667
no
0.4728915662650602
tl
0.4363929146537842
sk
0.42434210526315785
sl
0.37163375224416517
cs
0.3670886075949367
yo
0.36247723132969034
fi
0.3383742911153119
eu
0.3269230769230769
nl
0.31237721021611
sv
0.30417495029821073
de
0.29292929292929293
en
0.29149797570850206
hr
0.2753623188405797
lt
0.21171171171171171
lv
0.2009132420091324
vi
0.1935483870967742
ms
0.18032786885245902
tr
0.18032786885245902
reliable
true
passes
true
5
name
"Hunter"
dialogue
"Okay, okay. Let’s try this—point to where it happened. Or... or draw it if you have to."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8186330660557465
tl
0.6903520208604955
da
0.45961319681456203
fr
0.3725231175693527
pl
0.3233618233618234
yo
0.309593023255814
cs
0.3055555555555556
lv
0.30453879941434847
nl
0.2952522255192878
sq
0.2566510172143975
sk
0.21746293245469525
sl
0.2030201342281879
hr
0.19627749576988157
no
0.18664383561643835
lt
0.17962003454231434
sv
0.1739130434782609
de
0.1410488245931284
reliable
true
passes
true
6
name
"Maria"
dialogue
"Aquí... cerca del viejo granero. Escuché gritos."
detectedLang
"es"
heavyLang
"es"
scores
es
0.7682119205298014
ca
0.6669838249286394
it
0.6391752577319588
pt
0.5736906211936663
cs
0.40374787052810895
ro
0.3934142114384749
tl
0.38811188811188807
fr
0.35185185185185186
sv
0.32432432432432434
no
0.31906614785992216
da
0.3137254901960784
sk
0.31237721021611
sl
0.30966469428007887
lt
0.3027888446215139
fi
0.19908466819221968
pl
0.16666666666666666
en
0.1606714628297362
hr
0.1606714628297362
yo
0.1606714628297362
de
0.14425427872860636
nl
0.14425427872860636
sq
0.14425427872860636
reliable
true
passes
true
7
name
"Hunter"
dialogue
"Look, I gotta go. But stay in town, alright? We’ll figure this out."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7957712638154734
tl
0.5948522402287894
it
0.5545073375262054
ro
0.4713930348258706
yo
0.43408788282290284
sv
0.4310575635876841
pl
0.4279946164199193
fr
0.4209809264305177
de
0.40559440559440557
no
0.4039270687237027
da
0.3988684582743989
ca
0.3359375
sq
0.33176100628930816
hu
0.2916666666666667
nl
0.2685025817555938
sl
0.2659758203799654
az
0.256993006993007
hr
0.24645390070921988
fi
0.2085661080074488
cs
0.19811320754716982
ms
0.15
sk
0.1448692152917505
be
0.1414141414141414
tr
0.1414141414141414
es
0.13967611336032387
pt
0.13967611336032387
et
0.1290983606557377
is
0.1290983606557377
lt
0.1290983606557377
lv
0.1290983606557377
uk
0.1290983606557377
vi
0.1290983606557377
reliable
true
passes
true
8
name
"Maria"
dialogue
"Lo intentaré... pero tenga cuidado."
detectedLang
"es"
heavyLang
"es"
scores
es
0.7965641952983725
pt
0.6892265193370166
it
0.6287128712871286
ca
0.6059544658493871
tl
0.5697896749521989
fr
0.5302713987473904
ms
0.5273109243697479
no
0.4955156950672646
cs
0.4874715261958998
ro
0.4498777506112469
en
0.4260204081632653
pl
0.42159383033419023
sl
0.4109947643979057
lt
0.4063324538258575
vi
0.4063324538258575
de
0.4015957446808511
hr
0.39999999999999997
hu
0.3951612903225807
eu
0.39189189189189183
sq
0.39189189189189183
da
0.3885869565217392
nl
0.38524590163934425
sv
0.38524590163934425
yo
0.3784530386740331
sk
0.3732590529247911
is
0.3283582089552239
lv
0.27652733118971057
fi
0.24242424242424243
tr
0.24242424242424243
et
0.23728813559322032
az
0.22945205479452058
reliable
true
passes
true
9
name
"Hunter"
dialogue
"Yeah. You too."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7807017543859649
cs
0.5098039215686274
tl
0.5098039215686274
reliable
true
passes
true