Run: 2026-02-25-01KJ94Y6P529WJB0M446YMX7FK

Run Details

Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
11.4s
Cost:
$0.004995
Provider:
Google AI Studio

Evaluation summary

Score Evaluator
Details Link
62.50% 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

AI
Hunter: "Excuse me, miss? I’m Detective Hunter with the local PD. I’m sorry to bother you, but I’m investigating the disappearances near the old orchard. People noticed you out there earlier with your camera. Did you see anything unusual near the treeline yesterday evening?" Selvi: "Aap... aap police se hain? Shukr hai! Maine wahan kuch bahut bura dekha. Main photo le rahi thi aur achanak... wahan koi tha. Woh cheekh raha tha, aur phir sab shaant ho gaya. Mujhe bahut darr lag raha hai." Hunter: "Whoa, slow down. I—I don’t speak... is that Hindi? I’m sorry, I don’t understand. Look, I’m just trying to find out if you saw a man in a red flannel shirt. Tall, local guy? Here, look at this photo." Selvi: "Nahi, mera camera dekhiye! Maine wahan ki tasveerein li hain. Par jab maine piche mudkar dekha, toh wahan koi nahi tha. Sirf ye nishaan bache the... mitti mein khoon jaisa kuch tha. Kya aap meri baat samajh rahe hain? Hamein wahan jaana chahiye!" Hunter: "Look, I can see you’re shaken up, and I get the feeling you’re trying to tell me something important about the camera, but I’m not catching a word of it. I need to find someone in town who can translate for us. Just stay right here, okay? Don't move." Selvi: "Mujhe samajh nahi aa raha aap kya keh rahe hain, par kripya jaiye mat! Main akeli nahi rehna chahti. Woh cheez... woh abhi bhi wahan ho sakti hai. Alborn mein sab log khatre mein hain!" Hunter: "I’m sorry, I’m really trying to follow you, but—" (His phone vibrates aggressively in his pocket. He pulls it out and answers). "Hunter here. What? At the Apple Festival grounds? Another one? Right now? Dammit. I’m three minutes away. Secure the perimeter, I’m coming in hot." Hunter: "Listen, I have to go—an emergency just broke. I’ll come back for you, okay? Stay in this cafe. It’s the safest place in Alborn right now. Just... stay put!"
created_at"2026-02-25T00:59:43.692Z" 2/25/2026, 12:59:43 AM
model"google/gemini-3-flash-preview-20251217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1718
moderation_latency(null)
generation_time11337
tokens_prompt315
tokens_completion906
native_tokens_prompt289
native_tokens_completion1617
native_tokens_completion_images0
native_tokens_reasoning1093
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"STOP"
usage0.0049955
router(null)
provider_responses
0
endpoint_id"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byokfalse
latency1718
model_permaslug"google/gemini-3-flash-preview-20251217"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771981183-calT9Jihr4A0Gee5IS9g"
upstream_id(null)
total_cost0.0049955
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"

Evaluation details

Result Evaluator Details Meta Data
62.50% Parse dialogue n/a
dialogue
0
name"Hunter"
dialogue"Excuse me, miss? I’m Detective Hunter with the local PD. I’m sorry to bother you, but I’m investigating the disappearances near the old orchard. People noticed you out there earlier with your camera. Did you see anything unusual near the treeline yesterday evening?"
detectedLang"en"
heavyLang"en"
scores
en0.7884770346494763
tl0.6341463414634145
fr0.4950304584802822
nl0.47830407419675386
pt0.46772558296721867
it0.4550173010380623
ro0.45331482124262407
no0.41881918819188196
es0.39724454649827784
ms0.38500585708707535
da0.3804091266719119
de0.34890450599421247
ca0.3423799582463466
et0.3283582089552239
sv0.3089074155331285
sq0.2996887505558026
sl0.2482100238663485
cs0.22982885085574573
hr0.2206828302820386
sk0.20534813319878908
lv0.19642857142857142
is0.136039495337356
yo0.13413963716327654
lt0.12742382271468145
tr0.11715246636771301
fi0.1151685393258427
pl0.07894736842105263
az0.06969875959834614
ja0.03610771113831089
reliabletrue
passestrue
1
name"Selvi"
dialogue"Aap... aap police se hain? Shukr hai! Maine wahan kuch bahut bura dekha. Main photo le rahi thi aur achanak... wahan koi tha. Woh cheekh raha tha, aur phir sab shaant ho gaya. Mujhe bahut darr lag raha hai."
detectedLang"fr"
heavyLang"vi"
scores
fr0.48809523809523814
en0.3980963045912654
ro0.38111686816350027
tl0.377533294730747
it0.3635287152161042
ms0.33105164903546985
cs0.32262129804662887
fi0.28902116402116407
sq0.27900737759892685
sl0.2765814266487214
et0.2677111716621254
hr0.2636986301369863
de0.2621825669183253
no0.25759668508287287
eu0.2354196301564723
es0.2315939957112223
vi0.22494592645998557
pt0.2118768328445748
ca0.21129860601614087
hu0.20193021529324423
sk0.19955323901712585
sv0.19955323901712585
yo0.17561349693251532
da0.14478918058870327
az0.14342629482071714
lv0.1413738019169329
nl0.13166397415185782
tr0.12029459901800327
pl0.07566638005159072
lt0.07487091222030981
hi0.06684027777777778
reliablefalse
passesfalse
2
name"Hunter"
dialogue"Whoa, slow down. I—I don’t speak... is that Hindi? I’m sorry, I don’t understand. Look, I’m just trying to find out if you saw a man in a red flannel shirt. Tall, local guy? Here, look at this photo."
detectedLang"en"
heavyLang"en"
scores
en0.7934997306518226
tl0.6840659340659341
da0.4877505567928731
no0.43041109460128774
sv0.4244244244244244
nl0.3895966029723991
it0.37158469945355194
ro0.358974358974359
cs0.3495475113122172
yo0.3239271017048795
ca0.3162901307966707
pl0.3146603098927294
de0.3126120741183503
fr0.3059746529873265
sq0.3000608642726719
pt0.2780916509730069
hr0.2776381909547738
sl0.2767295597484277
sk0.2689129052765416
is0.25902061855670105
es0.2551813471502591
hu0.24688932547478712
lv0.23992068737607403
lt0.22973878097789682
et0.21875
ms0.17146974063400575
az0.15874177029992684
hi0.11877394636015325
tr0.1133384734001542
vi0.10366328916601715
be0.05737704918032788
eu0.05737704918032788
fi0.05193734542456719
uk0.05193734542456719
reliabletrue
passestrue
3
name"Selvi"
dialogue"Nahi, mera camera dekhiye! Maine wahan ki tasveerein li hain. Par jab maine piche mudkar dekha, toh wahan koi nahi tha. Sirf ye nishaan bache the... mitti mein khoon jaisa kuch tha. Kya aap meri baat samajh rahe hain? Hamein wahan jaana chahiye!"
detectedLang"fi"
heavyLang"vi"
scores
fi0.3684461391801716
de0.3638982237157945
fr0.33650475713570355
et0.3187660668380463
tl0.3066457352171638
sv0.2837837837837838
ms0.25936277249860257
ro0.2564534231200898
it0.2543612830613393
lv0.24929178470254953
en0.2419908466819222
yo0.20658682634730538
eu0.18611793611793614
tr0.17548226509023024
da0.1624525916561315
nl0.15766052129688493
ca0.13849154746423928
is0.12886259040105194
no0.1282894736842105
sq0.1282894736842105
az0.10533423362592842
sl0.10351826792963464
hu0.08367911479944676
hr0.07082748948106592
es0.06952247191011236
cs0.05894886363636364
lt0.052894924946390275
pl0.052894924946390275
reliablefalse
passesfalse
4
name"Hunter"
dialogue"Look, I can see you’re shaken up, and I get the feeling you’re trying to tell me something important about the camera, but I’m not catching a word of it. I need to find someone in town who can translate for us. Just stay right here, okay? Don't move."
detectedLang"en"
heavyLang"en"
scores
en0.8242118832766905
tl0.637593621647741
no0.46808510638297873
nl0.4113029827315541
it0.410840534171249
da0.40898345153664306
ca0.3946731234866829
ro0.39295831647106433
fr0.3760399334442596
yo0.375
sv0.37027707808564225
de0.3365767359575409
es0.336283185840708
sq0.33540097474523706
pt0.3315508021390375
et0.3153811045184847
ms0.28842504743833014
pl0.25742574257425743
sl0.25447316103379725
hr0.2518703241895262
tr0.22879177377892032
cs0.22158796056045665
lv0.21383647798742136
sk0.2092778070637849
lt0.20508744038155804
az0.19050188882892607
is0.17898193760262726
hu0.1294254207777133
vi0.1284137129575828
fi0.08424908424908424
eu0.08368967623701894
be0.0445859872611465
uk0.04030710172744722
reliabletrue
passestrue
5
name"Selvi"
dialogue"Mujhe samajh nahi aa raha aap kya keh rahe hain, par kripya jaiye mat! Main akeli nahi rehna chahti. Woh cheez... woh abhi bhi wahan ho sakti hai. Alborn mein sab log khatre mein hain!"
detectedLang"ms"
heavyLang"tl"
scores
ms0.3148502230720204
no0.27266576454668473
et0.24930167597765363
fr0.2326909350463954
sq0.22661870503597123
fi0.22044960116026108
eu0.21988388969521042
lv0.1899020346646571
sv0.1874527588813303
tl0.17498081350729086
ca0.17371252882398155
it0.16081186572989853
en0.15949960906958563
de0.1588419405320814
is0.14750198255352892
sk0.14750198255352892
da0.14274322169059012
vi0.12743506493506493
cs0.08975444538526672
ro0.08041060735671514
lt0.06521739130434782
reliablefalse
passesfalse
6
name"Hunter"
dialogue"Hunter here. What? At the Apple Festival grounds? Another one? Right now? Dammit. I’m three minutes away. Secure the perimeter, I’m coming in hot."
detectedLang"en"
heavyLang"en"
scores
en0.8
tl0.6828933836133013
fr0.5548604427333975
da0.5116156282998944
sv0.5066666666666667
no0.491478834524464
nl0.4841048522030117
de0.47233314318311465
es0.4702176403207331
it0.4390539721043057
ro0.4156664560960202
ms0.3946335078534032
ca0.38415446071904125
sq0.3804420629604822
pt0.3707482993197279
sl0.3655692729766804
hr0.30918595967139656
et0.29389312977099236
pl0.2430441898527005
yo0.2252931323283082
cs0.22072451558550968
sk0.21940928270042195
lt0.21142369991474852
fi0.18141592920353983
az0.17923691215616683
tr0.1621376811594203
lv0.11652340019102196
hu0.06754032258064516
reliabletrue
passestrue
7
name"Hunter"
dialogue"Listen, I have to go—an emergency just broke. I’ll come back for you, okay? Stay in this cafe. It’s the safest place in Alborn right now. Just... stay put!"
detectedLang"en"
heavyLang"en"
scores
en0.8053451178451178
tl0.6513381078024877
da0.5438856015779093
no0.4750283768444949
pl0.4247512437810945
yo0.41787287602265577
sv0.4160353535353536
it0.4104525175270874
fr0.37961099932930914
ro0.36730506155950754
de0.3664383561643836
nl0.36426116838487976
cs0.3607463718037318
hr0.3297101449275362
sl0.325309992706054
ca0.2812742812742813
pt0.24118129614438064
es0.23427152317880795
sq0.22916666666666666
lv0.22658862876254182
sk0.2213804713804714
ms0.2012089810017271
eu0.19284467713787085
tr0.18358340688437777
fi0.16891284815813118
vi0.1567912488605287
lt0.15293040293040291
et0.15137614678899083
az0.13712686567164178
hu0.13712686567164178
is0.12570888468809074
be0.07035175879396985
uk0.06376518218623482
reliabletrue
passestrue