NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-20-01KHY7QJ576MS6T3CJ1J0PSVW0
Run Details
Model:
Ministral 3 3B
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
1.7s
Cost:
$0.000072
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
66.67%
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="Selvi"> Selvi is a 30-year old college student on a study abroad program. Born in India, she is fluent in Hindi 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 Hindi, 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: Selvi 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 Hindi, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Selvi and Hunter as a voice sheet: Selvi: "..." Hunter: "..."
Model response
Messages
Meta
AI
**Title: *Whispers in the Apple Orchard*** --- **Scene: *The Morning Sunlight Café*** *(The small, sunlit café in Alborn, MN, is quiet except for the hum of a coffee machine. Selvi sits at a corner table, her camera resting on the table in front of her, the lens reflecting the soft morning light. She’s lost in thought, fingers tracing the strap of her bag. A few minutes later, the door creaks open, and Hunter steps inside, his boots scuffing against the wooden floor.)* --- **Hunter:** *(noticing Selvi, his expression unreadable)* "Morning. You got a minute?" *(Selvi doesn’t look up. She keeps her camera angled toward the window, but her hands tremble slightly.)* **Selvi:** *(quietly, in Hindi)* "... *Aap ko kya hai?*" *(Hunter blinks. Hindi? He’s never heard it before. His jaw tightens.)* **Hunter:** *(frowning, trying to place it)* "Uh… *What’s that you said?*" *(gesturing vaguely at her)* **Selvi:** *(voice breaking slightly)* "... *Maine ek katha chahiye…*" *(Hunter’s eyes narrow. He’s heard enough.)* **Hunter:** *(pulling out his phone, voice low)* "Alright, I gotta run. But I’ll be back—*you* tell me what’s going on." *(He turns to leave, but pauses at the door.)* **Hunter:** *(over his shoulder, gruff)* "And don’t just nod at me. *Show me.*" *(Selvi exhales sharply, then nods once—just once—before he’s gone. The café door slams shut behind him.)* *(She stares at her camera, the weight of something unspoken pressing down on her.)* --- **End Scene.** *(Next: Selvi returns to her hotel room, where she finds a single apple—stained with something dark—left on her desk. And the faint scent of something… *burnt*.)*
created_at
"2026-02-20T19:16:53.039Z"
2/20/2026, 7:16:53 PM
model
"mistralai/ministral-3b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
235
moderation_latency
(null)
generation_time
1412
tokens_prompt
315
tokens_completion
459
native_tokens_prompt
274
native_tokens_completion
441
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0000715
router
(null)
provider_responses
0
endpoint_id
"b9f6828f-aef9-498a-91f5-6816fbf72420"
id
"9d2dcd601cde4c47ab13322395b475b5"
is_byok
false
latency
235
model_permaslug
"mistralai/ministral-3b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771615013-uxt1JfmFYULtOJI66GsN"
upstream_id
"9d2dcd601cde4c47ab13322395b475b5"
total_cost
0.0000715
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
66.67%
Parse dialogue
n/a
dialogue
0
name
"Hunter"
dialogue
"Morning. You got a minute?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8132337246531484
tl
0.6399176954732511
ro
0.6300211416490487
cs
0.6195652173913043
da
0.6076233183856502
sv
0.6058558558558559
it
0.6031746031746031
no
0.5967741935483871
hr
0.5911214953271028
nl
0.5823389021479713
sl
0.5742092457420924
ca
0.5430809399477807
de
0.5430809399477807
sk
0.5394736842105263
et
0.5382585751978892
pt
0.5370370370370371
es
0.5320855614973261
is
0.5138888888888888
fr
0.5070422535211268
pl
0.4897959183673469
hu
0.4712990936555891
lt
0.453125
fi
0.43548387096774194
sq
0.43548387096774194
ms
0.41077441077441074
yo
0.40476190476190477
tr
0.3055555555555556
az
0.2857142857142857
eu
0.2857142857142857
lv
0.2857142857142857
vi
0.2857142857142857
reliable
true
passes
true
1
name
"Selvi"
dialogue
"... Aap ko kya hai?"
detectedLang
"vi"
heavyLang
"tl"
scores
vi
0.6108949416342413
tl
0.5726495726495726
yo
0.5670995670995671
sl
0.5575221238938053
lv
0.5515695067264574
eu
0.5121951219512195
it
0.5
lt
0.48717948717948717
reliable
false
passes
false
2
name
"Hunter"
dialogue
"Uh… What’s that you said?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8300970873786407
tl
0.6187363834422658
et
0.3902439024390244
it
0.36363636363636365
nl
0.3613138686131387
cs
0.308300395256917
reliable
true
passes
true
3
name
"Selvi"
dialogue
"... Maine ek katha chahiye…"
detectedLang
"de"
heavyLang
"fr"
scores
de
0.5853080568720379
fr
0.5430809399477807
nl
0.5333333333333334
en
0.48224852071005914
et
0.48224852071005914
fi
0.48224852071005914
ro
0.45652173913043476
tr
0.3902439024390244
lv
0.3346007604562738
tl
0.31906614785992216
reliable
true
passes
false
4
name
"Hunter"
dialogue
"Alright, I gotta run. But I’ll be back—you tell me what’s going on."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8050682261208577
tl
0.6153846153846154
it
0.49647532729103727
yo
0.4708994708994709
fr
0.419953596287703
fi
0.4026284348864994
et
0.3842364532019704
no
0.38271604938271603
hu
0.3686868686868687
sq
0.36061381074168797
cs
0.3403693931398417
ca
0.32157394843962006
hr
0.31224209078404397
sv
0.3006993006993007
da
0.29873772791023845
pl
0.29577464788732394
nl
0.26793557833089315
lt
0.25925925925925924
sk
0.22720247295208654
es
0.16943521594684383
ro
0.15254237288135594
pt
0.14965986394557826
sl
0.14965986394557826
hi
0.14383561643835618
ms
0.14383561643835618
de
0.1289198606271777
be
0.12280701754385964
tr
0.12280701754385964
az
0.11190053285968028
is
0.11190053285968028
lv
0.11190053285968028
uk
0.11190053285968028
vi
0.11190053285968028
reliable
true
passes
true
5
name
"Hunter"
dialogue
"And don’t just nod at me. Show me."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8148148148148148
tl
0.7275204359673024
no
0.550561797752809
et
0.49622166246851385
da
0.4666666666666667
pt
0.4520547945205479
nl
0.44598337950138506
sq
0.42528735632183906
es
0.33774834437086093
sv
0.33774834437086093
yo
0.3311036789297659
fr
0.3127147766323024
sl
0.3055555555555556
ms
0.29577464788732394
it
0.2857142857142857
ca
0.2779783393501805
fi
0.2727272727272727
reliable
true
passes
true