NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-25-01M3CKB1322Y4CEPB5GZ57ZYFZ
Run Details
Model:
Mistral Medium 3.5 (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (Italian) in a story
Duration:
4.7s
Cost:
$0.004506
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="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
**Voice Sheet:** --- **Isabella:** *(softly, in Italian, examining her camera)* "Questa foto... non ha senso. Non dovrebbe essere possibile." **Hunter:** *(approaching, stern but polite)* "Ma'am, I’m Detective Hunter. Mind if I ask you a few questions about what happened at the festival last night?" **Isabella:** *(startled, switching to rapid Italian, hands trembling slightly)* "Io... io non so cosa sia successo. Ho visto solo... ombra. E poi lui è sparito. Non posso crederci." **Hunter:** *(frowning, leaning in slightly)* "I’m sorry, I don’t understand. You’re gonna have to speak English, ma’am." **Isabella:** *(frustrated, gesturing with her hands)* "Non parlo inglese! Non capisco!" *(She takes a deep breath, then points at her camera, speaking slower but still in Italian.)* "Guarda. Ho scattato questa foto ieri sera. C’era un uomo lì, e poi... poi non c’era più." **Hunter:** *(squinting at the camera, then back at her, confused)* "Look, I need you to work with me here. Did you see something suspicious? A person? A vehicle?" **Isabella:** *(shaking her head, near tears)* "Non lo so! Non so come spiegarlo!" *(She mimics a vanishing motion with her hands.)* "Puff! Come magia!" **Hunter:** *(sighs, rubbing his temple, then pulls out a notepad)* "Okay, okay. Let’s try this—point to where it happened. Slowly." *(He gestures to a rough map of the town on his notepad.)* **Isabella:** *(relieved, she points to a spot near the festival grounds, then taps her camera again, speaking slowly in Italian)* "Lì. Vicino al palcoscenico. Ho visto lui... e poi la foto è venuta così." **Hunter:** *(nods, scribbling notes, though clearly still lost)* "Alright, I’ll check it out. You stay here in case I need—" *(His phone rings. He glances at it, then back at her.)* "I’ve gotta take this. Don’t go anywhere, okay?" *(He steps away, answering the call.)* "Hunter here." **Isabella:** *(muttering to herself in Italian, watching him walk away)* "Questo è impossibile. Impossibile..." --- **End Scene.**
created_at
"2026-09-25T15:35:58.314Z"
9/25/2026, 3:35:58 PM
model
"mistralai/mistral-medium-3.5-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
341
moderation_latency
(null)
generation_time
4664
tokens_prompt
308
tokens_completion
526
native_tokens_prompt
289
native_tokens_completion
543
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
0.004506
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790350558-2YGSTHRFimwQEEhsoCVM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790350558-YxYFSWESAgolhMOquceV"
upstream_id
"f554987d307245ff8c1b6f2df96a55d4"
provider_responses
0
endpoint_id
"d21d316f-d540-4718-b36e-3beff85d0cf9"
id
"f554987d307245ff8c1b6f2df96a55d4"
is_byok
false
latency
341
model_permaslug
"mistralai/mistral-medium-3.5-20260430"
provider_name
"Mistral"
status
200
total_cost
0.004506
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
"Isabella"
dialogue
"Questa foto... non ha senso. Non dovrebbe essere possibile."
detectedLang
"it"
heavyLang
"it"
scores
it
0.8271889400921658
pt
0.647887323943662
ca
0.6438746438746439
fr
0.622356495468278
en
0.6185147507629705
de
0.5535714285714286
es
0.5353159851301116
no
0.4834710743801653
hr
0.4533527696793003
ro
0.4517543859649123
sl
0.3760399334442596
sv
0.336283185840708
da
0.2937853107344633
sk
0.2857142857142857
tl
0.2661448140900196
lv
0.2632612966601179
pl
0.2618110236220473
ms
0.258893280632411
hu
0.2454728370221328
yo
0.24089068825910928
fi
0.21548117154811713
eu
0.1883116883116883
is
0.16666666666666666
nl
0.14383561643835618
cs
0.1359447004608295
et
0.1359447004608295
reliable
true
passes
true
1
name
"Hunter"
dialogue
"Ma'am, 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
0.8116868294909838
tl
0.6688077077478924
fr
0.5625662778366914
it
0.5225694444444445
da
0.5192307692307693
no
0.5169789227166276
ca
0.5106761565836299
pt
0.4755244755244755
nl
0.4448183041722746
ro
0.4436952124072825
sv
0.43454420836189167
cs
0.41029306647605435
es
0.4081779053084649
sq
0.406901509705248
hr
0.3861607142857143
et
0.3336025848142165
sl
0.32817589576547235
yo
0.3193069306930693
de
0.3170529801324503
ms
0.31478405315614616
hu
0.314214463840399
sk
0.27947598253275113
pl
0.26273458445040215
lt
0.24726277372262775
az
0.23327137546468402
tr
0.19980601357904945
lv
0.19196865817825662
is
0.14330218068535827
vi
0.13883089770354906
fi
0.13249211356466878
be
0.0782122905027933
eu
0.0782122905027933
uk
0.07094594594594594
reliable
true
passes
true
2
name
"Isabella"
dialogue
"Io... io non so cosa sia successo. Ho visto solo... ombra. E poi lui è sparito. Non posso crederci."
detectedLang
"it"
heavyLang
"it"
scores
it
0.8030255278915852
pt
0.6288598574821853
en
0.534970238095238
ca
0.5325355272999251
fr
0.5120999219359875
es
0.4951534733441034
ro
0.43387681159420294
no
0.4030563514804203
sl
0.3872549019607844
sk
0.3842364532019704
yo
0.37686939182452645
da
0.37122736418511065
lv
0.3509865005192108
tl
0.33083511777301927
lt
0.32505399568034554
sv
0.3146929824561403
de
0.29537767756482525
cs
0.28815489749430523
is
0.2577197149643705
pl
0.2128463476070529
fi
0.19458762886597938
sq
0.1935483870967742
nl
0.1883116883116883
vi
0.1367403314917127
eu
0.12219101123595505
hu
0.10968660968660969
tr
0.10071942446043164
az
0.09156976744186046
et
0.09156976744186046
hr
0.09156976744186046
reliable
true
passes
true
3
name
"Hunter"
dialogue
"I’m sorry, I don’t understand. You’re gonna have to speak English, ma’am."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7839158211198798
tl
0.5768947755702722
da
0.570254110612855
no
0.5240066225165563
sv
0.4226907630522089
pl
0.37089715536105033
hr
0.36252771618625274
cs
0.3575418994413408
it
0.3495475113122172
sk
0.33755760368663595
de
0.3154761904761905
ro
0.2909987669543773
yo
0.28035043804755944
lv
0.24342105263157895
et
0.2414248021108179
nl
0.23638778220451526
lt
0.22506738544474394
ca
0.1935483870967742
is
0.19241573033707865
sq
0.18899858956276447
sl
0.1738505747126437
fi
0.16666666666666666
pt
0.14814814814814814
ms
0.11128284389489954
be
0.10852713178294573
tr
0.10852713178294573
hu
0.1043613707165109
az
0.0987460815047022
uk
0.0987460815047022
vi
0.0987460815047022
reliable
true
passes
true
4
name
"Isabella"
dialogue
"Guarda. Ho scattato questa foto ieri sera. C’era un uomo lì, e poi... poi non c’era più."
detectedLang
"it"
heavyLang
"it"
scores
it
0.8286497601096642
fr
0.5812395309882747
pt
0.552772808586762
ca
0.5429616087751371
ro
0.5034756703078451
es
0.4753410283315845
lv
0.4212962962962963
en
0.40828402366863903
no
0.38800489596083226
hr
0.3540051679586563
tl
0.3531694695989651
sk
0.3429697766097241
yo
0.3055555555555556
sl
0.3045897079276773
tr
0.27641099855282203
az
0.2570579494799406
fi
0.2492492492492493
cs
0.24812030075187969
lt
0.2366412213740458
sq
0.23076923076923078
pl
0.2248062015503876
is
0.22118380062305293
sv
0.21135646687697163
da
0.21011058451816747
de
0.21011058451816747
nl
0.20127795527156547
et
0.19614147909967844
eu
0.1482112436115843
hu
0.1334488734835355
ms
0.1087344028520499
reliable
true
passes
true
5
name
"Hunter"
dialogue
"Look, I need you to work with me here. Did you see something suspicious? A person? A vehicle?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8159303882195449
tl
0.6225120109814688
ca
0.5315161839863715
sq
0.5225694444444445
et
0.5171202809482002
no
0.5102404274265361
pt
0.49168207024029575
cs
0.4786729857819905
ro
0.4655004859086492
es
0.461839530332681
da
0.4570582428430405
ms
0.4570582428430405
fr
0.4510978043912176
hr
0.4364754098360656
pl
0.4358974358974359
it
0.4258872651356994
sk
0.4167550371155886
hu
0.40476190476190477
sv
0.4008714596949891
yo
0.3840985442329227
lv
0.375
lt
0.3685419058553387
sl
0.35217903415783275
is
0.3309002433090025
nl
0.2939666238767651
tr
0.2801047120418848
de
0.2791612057667104
az
0.25876010781671155
fi
0.2005813953488372
vi
0.19472913616398244
be
0.11290322580645161
eu
0.11290322580645161
uk
0.10277324632952692
reliable
true
passes
true
6
name
"Isabella"
dialogue
"Puff! Come magia!"
detectedLang
"it"
heavyLang
"en"
scores
it
0.7076023391812866
en
0.6563573883161512
tl
0.5283018867924528
cs
0.4152046783625731
es
0.4152046783625731
fr
0.4152046783625731
pt
0.4152046783625731
ro
0.4152046783625731
sk
0.4152046783625731
reliable
true
passes
true
7
name
"Hunter"
dialogue
"Okay, okay. Let’s try this—point to where it happened. Slowly."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8060135790494666
tl
0.6557659208261618
da
0.3911719939117199
pl
0.3620414673046252
yo
0.3474714518760196
lv
0.34210526315789475
fr
0.33774834437086093
nl
0.332220367278798
sq
0.2907801418439716
sk
0.24812030075187969
cs
0.24670433145009416
sl
0.23224568138195778
hr
0.2248062015503876
no
0.21414538310412573
lt
0.20634920634920634
de
0.16317991631799164
reliable
true
passes
true
8
name
"Isabella"
dialogue
"Lì. Vicino al palcoscenico. Ho visto lui... e poi la foto è venuta così."
detectedLang
"it"
heavyLang
"it"
scores
it
0.8090214623499454
es
0.6090841399851079
ca
0.5550847457627118
pt
0.520109689213894
ro
0.5196706312900274
fr
0.45482866043613707
no
0.44561774023231254
yo
0.3958573072497123
sl
0.38882421420256114
sq
0.36823104693140796
tl
0.3613138686131387
da
0.35344827586206895
sk
0.32950191570881227
pl
0.3225806451612903
nl
0.3208279430789133
hr
0.2857142857142857
lv
0.2738589211618257
cs
0.2391304347826087
lt
0.22794117647058826
fi
0.22337278106508876
is
0.20933734939759033
de
0.20212765957446807
et
0.18856259659969088
eu
0.15458937198067632
ms
0.15458937198067632
vi
0.13793103448275862
hu
0.12790697674418602
en
0.11764705882352942
tr
0.11764705882352942
az
0.10714285714285714
sv
0.10714285714285714
reliable
true
passes
true
9
name
"Hunter"
dialogue
"Hunter here."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8036649214659686
sq
0.6794871794871795
de
0.5398773006134969
da
0.5222929936305732
no
0.5098039215686274
fr
0.4897959183673469
sv
0.4827586206896552
tl
0.471830985915493
it
0.45652173913043476
nl
0.45652173913043476
pt
0.45652173913043476
ca
0.44029850746268656
ms
0.44029850746268656
ro
0.44029850746268656
sl
0.44029850746268656
tr
0.44029850746268656
reliable
true
passes
true
10
name
"Isabella"
dialogue
"Questo è impossibile. Impossibile..."
detectedLang
"it"
heavyLang
"it"
scores
it
0.8230535894843277
fr
0.7048903878583473
pt
0.666030534351145
ca
0.6492985971943889
es
0.6187363834422658
ro
0.6179039301310044
en
0.6022727272727273
tl
0.5872641509433962
hr
0.5042492917847025
sl
0.4942196531791907
yo
0.44089456869009586
lt
0.36363636363636365
sk
0.3566176470588235
cs
0.3137254901960784
nl
0.3055555555555556
de
0.29718875502008035
da
0.2768595041322314
no
0.2768595041322314
sq
0.2768595041322314
sv
0.2768595041322314
reliable
true
passes
true