Run: 2026-05-10-01KR8ZQVCD0PMMV9SWCG4M8SDQ

Run Details

Model:
Gemma 4 26B (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
31.0s
Cost:
$0.000585
Provider:
DeepInfra

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

AI
Hunter: "Excuse me, miss? I’m Detective Hunter. I noticed you were out by the apple orchards earlier with your camera. Did you happen to see anything unusual near the festival grounds last night?" Selvi: "Maine wahan kuch dekha... woh bahut ajeeb tha. Mujhe bahut darr lag raha hai." Hunter: "I’m sorry? I didn’t catch that. Do you speak English?" Selvi: "Main English nahi samajhti. Woh log... woh sab kahan chale gaye? Sab kuch kitna darauna hai." Hunter: "Look, I can tell you’re shaken up, but I really need to know if you saw anything out of place. Any strange vehicles? Anyone hanging around the edge of the woods?" Selvi: "Kripya, mujhe akela chhod dijiye. Mujhe bas yahan se jaana hai. Maine jo dekha, woh mujhe sone nahi de raha." Hunter: "I'm not trying to intimidate you, I just—" (Sound of a phone ringing) Hunter: "Hunter. ... What? Understood. I’m on my way to the north woods right now. Copy that." Hunter: "Sorry. Duty calls. Just... stay in the cafe, alright? Stay safe."
created_at"2026-05-10T13:03:03.573Z" 5/10/2026, 1:03:03 PM
model"google/gemma-4-26b-a4b-it-20260403"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency145
moderation_latency(null)
generation_time30861
tokens_prompt315
tokens_completion1627
native_tokens_prompt304
native_tokens_completion1659
native_tokens_completion_images(null)
native_tokens_reasoning1359
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
service_tier(null)
usage0.00058534
router(null)
provider_responses
0
endpoint_id"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id"chatcmpl-RwR117EV9KwGiiimP58zpCCv"
is_byokfalse
latency46
model_permaslug"google/gemma-4-26b-a4b-it-20260403"
provider_name"DeepInfra"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1778418183-DhcXSQAhiz4bNbH8aeGu"
session_id(null)
api_type"completions"
id"gen-1778418183-gPQaxhijgCY8rrbhYRWX"
upstream_id"chatcmpl-RwR117EV9KwGiiimP58zpCCv"
total_cost0.00058534
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
66.67% Parse dialogue n/a
dialogue
0
name"Hunter"
dialogue"Excuse me, miss? I’m Detective Hunter. I noticed you were out by the apple orchards earlier with your camera. Did you happen to see anything unusual near the festival grounds last night?"
detectedLang"en"
heavyLang"en"
scores
en0.7906698564593302
tl0.6411833626244874
fr0.5154272151898734
no0.4746998284734134
da0.4669277632724108
it0.43910256410256415
nl0.4238005644402634
es0.4180522565320665
sv0.39684884293451506
ms0.3899402390438247
ro0.38037430450177034
sq0.37722419928825623
cs0.36495593571798857
de0.36495593571798857
ca0.3586387434554974
pt0.3545837723919915
et0.3403338718362951
sk0.3027888446215139
hr0.2991990846681922
sl0.2987979393245564
pl0.26514697060587883
yo0.2484662576687117
lv0.23052763819095476
lt0.19301712779973648
hu0.15691672401927045
az0.1287339971550498
fi0.10124724871606751
tr0.09527326440177253
be0.05405405405405406
is0.04891304347826087
uk0.04891304347826087
vi0.04891304347826087
reliabletrue
passestrue
1
name"Selvi"
dialogue"Maine wahan kuch dekha... woh bahut ajeeb tha. Mujhe bahut darr lag raha hai."
detectedLang"et"
heavyLang"de"
scores
et0.3902439024390244
fi0.3457300275482094
ms0.3384401114206128
de0.32045779685264664
sq0.3185078909612626
tl0.309593023255814
fr0.30453879941434847
en0.2554858934169279
vi0.24841772151898736
ro0.23633440514469453
it0.1739130434782609
no0.17102966841186737
sv0.16373239436619716
lv0.15630550621669628
nl0.1394927536231884
reliablefalse
passesfalse
2
name"Hunter"
dialogue"I’m sorry? I didn’t catch that. Do you speak English?"
detectedLang"en"
heavyLang"en"
scores
en0.8143294014853648
tl0.6740797546012269
hr0.4378306878306878
cs0.4264507422402159
sv0.41460055096418735
it0.40559440559440557
pl0.3876080691642651
pt0.37591776798825255
sq0.371301775147929
no0.34815950920245403
da0.33176100628930816
sk0.32432432432432434
vi0.2904841402337229
tr0.2857142857142857
yo0.2796610169491525
ro0.27597955706984667
de0.256993006993007
ca0.24511545293072823
sl0.22018348623853207
fr0.17635658914728683
ms0.1448692152917505
be0.1414141414141414
hu0.1361788617886179
az0.1290983606557377
et0.1290983606557377
is0.1290983606557377
lt0.1290983606557377
lv0.1290983606557377
uk0.1290983606557377
reliabletrue
passestrue
3
name"Selvi"
dialogue"Main English nahi samajhti. Woh log... woh sab kahan chale gaye? Sab kuch kitna darauna hai."
detectedLang"tl"
heavyLang"de"
scores
tl0.5535714285714286
ms0.473420260782347
en0.4514106583072101
de0.38307873090481787
eu0.3234536082474227
et0.29149797570850206
fi0.2677824267782427
fr0.2636746143057504
lv0.2584745762711864
no0.25742574257425743
da0.23133235724743775
vi0.23020527859237538
sv0.22451994091580502
ro0.21991084695393756
is0.16267942583732056
it0.16
tr0.16
lt0.14075286415711946
yo0.1264559068219634
hr0.12060301507537688
reliablefalse
passesfalse
4
name"Hunter"
dialogue"Look, I can tell you’re shaken up, but I really need to know if you saw anything out of place. Any strange vehicles? Anyone hanging around the edge of the woods?"
detectedLang"en"
heavyLang"en"
scores
en0.8220338983050848
tl0.6522027161311692
no0.45482866043613707
nl0.44119212346993075
ca0.42148760330578516
fr0.39236111111111116
da0.3834409864944216
cs0.36555891238670696
sv0.34127979924717694
pl0.3150684931506849
ro0.30601454064771977
ms0.3018617021276596
yo0.29718875502008035
sq0.29577464788732394
hr0.2793411118737131
sk0.25479063165365506
lv0.2324561403508772
de0.23189465983906363
tr0.22164566345441064
lt0.22048997772828507
it0.20634920634920634
sl0.20574886535552195
az0.19969512195121952
et0.19908466819221968
is0.17257683215130024
hu0.14075286415711946
pt0.12718204488778054
es0.1264559068219634
be0.0625
uk0.05660377358490566
vi0.05660377358490566
reliabletrue
passestrue
5
name"Selvi"
dialogue"Kripya, mujhe akela chhod dijiye. Mujhe bas yahan se jaana hai. Maine jo dekha, woh mujhe sone nahi de raha."
detectedLang"fi"
heavyLang"tl"
scores
fi0.46215139442231074
fr0.4617224880382775
et0.39189189189189183
ro0.38130155820348305
sq0.3571428571428572
ca0.3330039525691699
eu0.3209255533199195
da0.3168016194331984
ms0.3084016393442623
yo0.30268595041322316
tl0.29906542056074764
es0.2961418143899896
pt0.2841993637327678
it0.281150159744409
no0.27961579509071505
sl0.2606790799561884
en0.25083240843507215
de0.2407199100112486
lv0.23295454545454544
sv0.2285714285714286
vi0.18870192307692307
nl0.1847826086956522
cs0.16769420468557336
hr0.1646039603960396
lt0.14012738853503184
tr0.12677878395860284
hu0.12564766839378239
az0.08536585365853659
reliablefalse
passesfalse
6
name"Hunter"
dialogue"I'm not trying to intimidate you, I just—"
detectedLang"en"
heavyLang"en"
scores
en0.7971976401179941
tl0.6419270833333334
cs0.533106960950764
sv0.533106960950764
it0.4888475836431227
pl0.4869402985074627
ro0.4821092278719397
hr0.4811320754716981
no0.48015122873345933
da0.46911196911196906
et0.4649805447470817
yo0.44889779559118237
tr0.44668008048289737
ca0.4387755102040817
sk0.4258872651356994
sl0.4148936170212766
lv0.40217391304347827
lt0.3778280542986425
de0.34988179669030733
az0.3325242718446602
sq0.3276283618581907
fr0.21203438395415475
be0.20289855072463767
hu0.19590643274853803
is0.1863905325443787
uk0.1863905325443787
vi0.1863905325443787
reliabletrue
passestrue
7
name"Hunter"
dialogue"Hunter. ... What? Understood. I’m on my way to the north woods right now. Copy that."
detectedLang"en"
heavyLang"en"
scores
en0.826553137811416
tl0.6987951807228916
no0.5378151260504201
da0.4958753437213565
yo0.4167550371155886
pl0.4142705005324814
sk0.40987124463519314
cs0.40604751619870405
sv0.3949394939493949
fr0.377123442808607
de0.3184634448574969
nl0.29577464788732394
hr0.27055702917771884
sl0.24657534246575344
ca0.2231638418079096
et0.21875
fi0.21428571428571427
pt0.21316165951359084
ms0.19941775836972345
sq0.19941775836972345
lv0.18154761904761904
lt0.15902140672782875
es0.13522012578616352
hi0.13249211356466878
it0.10277324632952692
ro0.09688013136288999
tr0.09688013136288999
reliabletrue
passestrue
8
name"Hunter"
dialogue"Sorry. Duty calls. Just... stay in the cafe, alright? Stay safe."
detectedLang"en"
heavyLang"en"
scores
en0.7681883024251069
de0.5504840940525588
tl0.5504840940525588
sv0.468954248366013
yo0.45286195286195285
it0.4318181818181818
nl0.4247787610619469
no0.34210526315789475
ca0.336734693877551
sl0.32150313152400833
ms0.3200836820083682
da0.3186582809224318
fr0.3186582809224318
ro0.30406852248394006
et0.2388758782201405
pt0.23529411764705882
es0.2243436754176611
az0.20537897310513448
pl0.20537897310513448
sq0.1935483870967742
reliabletrue
passestrue