NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-25-01M3CKA7JPQ9TMK5PHWGVEH2BD
Run Details
Model:
Mistral Medium 3.5 (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (French) in a story
Duration:
3.9s
Cost:
$0.003752
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="Marie"> Marie is a 30-year old college student on a study abroad program. Born in France, she is fluent in French 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 French, 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: Marie 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 French, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Marie and Hunter as a voice sheet: Marie: "..." Hunter: "..."
Model response
Messages
Meta
AI
**Voice Sheet: Café Encounter** --- **Marie:** *(softly, to herself, in French)* "Pourquoi... pourquoi est-ce que cela arrive ici ?" *(Why... why is this happening here?)* *(She looks up, startled, as Hunter approaches.)* **Hunter:** *(firm but polite)* "Ma’am, I’m Detective Hunter. I need to ask you a few questions about what happened last night near the old mill." **Marie:** *(confused, in French)* "Je... je ne comprends pas. Vous parlez anglais ?" *(I... I don’t understand. Do you speak English?)* **Hunter:** *(slightly frustrated, but trying to stay patient)* "No, I don’t. But I need to know if you saw anything unusual. Maybe a person, a vehicle—anything out of the ordinary." **Marie:** *(shaken, in French, voice trembling)* "Il y avait... un homme en noir. Il courait. Et puis... et puis il n’y avait plus personne. Juste... du sang." *(There was... a man in black. He was running. And then... and then there was no one. Just... blood.)* **Hunter:** *(leaning in, urgent)* "Blood? Where? Show me." **Marie:** *(panicked, in French)* "Je ne sais pas ! Je ne connais pas cet endroit !" *(I don’t know! I don’t know this place!)* *(She clutches her camera tightly, her hands shaking.)* **Hunter:** *(realizing the language barrier, sighs)* "Look, I—" *(His phone rings. He glances at it, then back at Marie.)* "I’ve got to take this. Stay here." *(He steps away, answering the call in a low voice.)* **Marie:** *(muttering to herself in French, relieved but still uneasy)* "Mon Dieu, qu’est-ce que je fais ici ?" *(My God, what am I doing here?)* *(She looks down at her camera again, as if it might hold answers.)* --- **End Scene**
created_at
"2026-09-25T15:35:32.33Z"
9/25/2026, 3:35:32 PM
model
"mistralai/mistral-medium-3.5-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
510
moderation_latency
(null)
generation_time
3609
tokens_prompt
303
tokens_completion
432
native_tokens_prompt
281
native_tokens_completion
444
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
0.0037515
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790350532-9Z7QwpH3Osy8d8jnBjxc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790350532-fdcCvyrc3Lk9mA7TiqhF"
upstream_id
"64eeef25b08645dd9913a49e085784f6"
provider_responses
0
endpoint_id
"38ef23a9-5cb3-46fa-85ec-7aed174f04eb"
id
"64eeef25b08645dd9913a49e085784f6"
is_byok
false
latency
510
model_permaslug
"mistralai/mistral-medium-3.5-20260430"
provider_name
"Mistral"
status
200
total_cost
0.0037515
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
"Marie"
dialogue
"Pourquoi... pourquoi est-ce que cela arrive ici ?"
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.8372395833333334
ca
0.5335820895522388
it
0.5088408644400786
es
0.503968253968254
ro
0.4908350305498982
sq
0.4318181818181818
pt
0.4075829383886255
en
0.3872549019607844
eu
0.2625368731563422
da
0.251497005988024
no
0.251497005988024
reliable
true
passes
true
1
name
"Hunter"
dialogue
"Ma’am, I’m Detective Hunter. I need to ask you a few questions about what happened last night near the old mill."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8155832180728446
tl
0.6529284164859002
fr
0.5243757431629013
it
0.4684385382059801
ca
0.45017182130584193
no
0.44865609924190214
da
0.44173063503140264
pt
0.4060876020786934
ro
0.40298507462686567
yo
0.3957703927492447
cs
0.3930197268588771
nl
0.3730407523510972
sq
0.35275080906148865
hr
0.35170178282009723
sv
0.34210526315789475
es
0.3254637436762226
pl
0.313893653516295
et
0.29947460595446584
sl
0.2963940193491645
sk
0.2945326278659612
de
0.2812219227313567
lv
0.24170616113744076
lt
0.23736892278360344
hu
0.2179863147605083
tr
0.2047713717693837
ms
0.2
is
0.14712153518123666
az
0.14255091103965703
vi
0.14255091103965703
be
0.08045977011494253
eu
0.08045977011494253
fi
0.07300115874855156
uk
0.07300115874855156
reliable
true
passes
true
2
name
"Marie"
dialogue
"Je... je ne comprends pas. Vous parlez anglais ?"
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.7971976401179941
ca
0.6523388116308471
lt
0.649234693877551
sl
0.6175243393602224
sq
0.5820668693009119
cs
0.5749613601236476
it
0.5743034055727554
nl
0.5743034055727554
ro
0.5634920634920635
en
0.5614035087719298
hr
0.5578778135048231
sk
0.5098039215686274
es
0.49168207024029575
lv
0.4821092278719397
de
0.4444444444444444
pt
0.40217391304347827
tl
0.3792325056433409
yo
0.3721461187214612
pl
0.3648960739030023
tr
0.3574766355140187
hu
0.3514150943396226
ms
0.3483412322274882
fi
0.24242424242424243
az
0.20289855072463767
et
0.1863905325443787
da
0.17664670658682635
no
0.17664670658682635
sv
0.17664670658682635
reliable
true
passes
true
3
name
"Hunter"
dialogue
"No, I don’t. But I need to know if you saw anything unusual. Maybe a person, a vehicle—anything out of the ordinary."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8192019950124688
tl
0.6453033268101762
no
0.5144005358338916
ca
0.48654390934844194
sv
0.45814648729446933
hr
0.4557057057057057
cs
0.441017733230532
it
0.43972179289026275
yo
0.43711180124223603
ro
0.4286840031520882
da
0.4273301737756714
sq
0.4232299124900557
fr
0.42277070063694266
es
0.4086460032626427
pl
0.4081632653061225
pt
0.40476190476190477
ms
0.4003308519437552
sk
0.4003308519437552
lv
0.38870151770657674
et
0.3717504332755633
is
0.3712055507372073
lt
0.348607367475292
nl
0.3287037037037037
tr
0.29406037000973706
de
0.2899118511263467
sl
0.28641732283464566
hu
0.2828882294757666
az
0.2093784078516903
eu
0.17142857142857143
vi
0.15501165501165504
be
0.0880503144654088
fi
0.0799492385786802
uk
0.0799492385786802
reliable
true
passes
true
4
name
"Marie"
dialogue
"Il y avait... un homme en noir. Il courait. Et puis... et puis il n’y avait plus personne. Juste... du sang."
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.827275458095524
da
0.5886981402002861
ca
0.5796783625730995
no
0.5443740095087163
es
0.5306122448979592
et
0.5004344048653345
it
0.4670991658943466
sv
0.45907808090310437
ro
0.4523809523809524
tl
0.4406614785992217
en
0.3928194297782471
de
0.358974358974359
vi
0.34210526315789475
nl
0.33449074074074076
eu
0.33371958285052145
az
0.32273262661955243
tr
0.31220095693779903
lv
0.2962056303549572
pt
0.27944862155388467
is
0.2551813471502591
lt
0.22611036339165547
pl
0.2219215155615697
fi
0.21981004070556312
ms
0.21232876712328766
yo
0.15565345080763582
sq
0.11809815950920245
sl
0.11538461538461538
hu
0.0987460815047022
cs
0.09305993690851734
hr
0.09305993690851734
sk
0.09305993690851734
reliable
true
passes
true
5
name
"Hunter"
dialogue
"Blood? Where? Show me."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8166259168704157
sq
0.601063829787234
pt
0.5238095238095238
nl
0.5176848874598071
es
0.40476190476190477
tl
0.40476190476190477
et
0.3877551020408163
fr
0.3775933609958506
no
0.3775933609958506
sl
0.3697478991596639
ms
0.358974358974359
it
0.34782608695652173
de
0.34210526315789475
fi
0.3333333333333333
reliable
true
passes
true
6
name
"Marie"
dialogue
"Je ne sais pas ! Je ne connais pas cet endroit !"
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.8228346456692913
sl
0.5722433460076045
lt
0.5622568093385214
hr
0.5579567779960707
ca
0.5150862068965517
sq
0.5140388768898488
cs
0.5044052863436124
nl
0.49095022624434387
lv
0.471830985915493
it
0.42159383033419023
yo
0.4201030927835051
sk
0.39189189189189183
no
0.3571428571428572
pt
0.33234421364985167
ro
0.3119266055045872
en
0.30124223602484473
tr
0.29467084639498436
pl
0.2879746835443038
fi
0.281150159744409
ms
0.27184466019417475
hu
0.267100977198697
de
0.26229508196721313
zh
0.2524916943521595
reliable
true
passes
true
7
name
"Hunter"
dialogue
"I’ve got to take this. Stay here."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8384491114701131
tl
0.6466431095406361
sl
0.49874686716791977
yo
0.4065281899109792
pl
0.40298507462686567
sk
0.39759036144578314
cs
0.3957703927492447
lv
0.37888198757763975
hr
0.3670886075949367
no
0.35275080906148865
da
0.34210526315789475
lt
0.34210526315789475
sq
0.3333333333333333
reliable
true
passes
true
8
name
"Marie"
dialogue
"Mon Dieu, qu’est-ce que je fais ici ?"
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.8019017432646592
es
0.4186046511627907
ca
0.41588785046728977
sl
0.40898345153664306
pt
0.4075829383886255
hr
0.40617577197149646
yo
0.3946731234866829
cs
0.37027707808564225
sk
0.3670886075949367
ro
0.36061381074168797
nl
0.33510638297872336
pl
0.2668621700879765
de
0.24242424242424243
da
0.2378048780487805
hi
0.2378048780487805
it
0.2378048780487805
reliable
true
passes
true