Run: 2026-04-24-01KQ0B163RQSGJNS3YT4A43K59

Run Details

Model:
GPT-OSS 120B
Test:
Language Writing
Scenario:
Character dialogue (German) in a story
Duration:
17.2s
Cost:
$0.000125
Provider:
Novita

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="Melanie"> Melanie is a 30-year old college student on a study abroad program. Born in Germany, she is fluent in German 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 German, 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: Melanie 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 German, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Melanie and Hunter as a voice sheet: Melanie: "..." Hunter: "..."

Model response

AI
Melanie: "Entschuldigung, ich… das ist alles zu schnell." Hunter: "Ma'am, I'm Detective Hunter. I'm looking into the recent disappearances. Did you see anything unusual at the café earlier today?" Melanie: "Ich habe nur Fotos gemacht. Aber ich hörte das laute Geräusch, als das Licht plötzlich ausging, und dann… niemand war mehr da." Hunter: "What do you mean 'nobody was there'?" Melanie: "Die Leute… sie waren weg, einfach so. Ich habe das Gefühl, dass etwas Schlimmes passiert ist." Hunter: "Did anyone mention a name? Any clue, a face, a license plate?" Melanie: "Ich… ich weiß nicht. Ich sah nur einen Mann mit einem dunklen Hut, der schnell ging, bevor das Licht ausging." Hunter: "Alright, that's helpful. If you remember anything else, call me, okay?" Melanie: "Ja, ich rufe Sie an, wenn mir etwas einfällt." Hunter: *[phone buzzes*] "Excuse me, I have to take this." *[steps away, glancing back, still puzzled]*
created_at"2026-04-24T18:11:32.098Z" 4/24/2026, 6:11:32 PM
model"openai/gpt-oss-120b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency553
moderation_latency(null)
generation_time17075
tokens_prompt319
tokens_completion472
native_tokens_prompt334
native_tokens_completion433
native_tokens_completion_images(null)
native_tokens_reasoning222
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"
usage0.00012495
router(null)
provider_responses
0
endpoint_id"3dc95f88-3960-4c91-b2bb-bbd2f5069c48"
id"652817c8bd02207297d4dd0303bc9c57"
is_byokfalse
latency441
model_permaslug"openai/gpt-oss-120b"
provider_name"Novita"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777054292-He3L3Ar6Gso1d4K4CP3T"
session_id(null)
api_type"completions"
id"gen-1777054292-nutyAa5QrPv3BGy2F72Y"
upstream_id"652817c8bd02207297d4dd0303bc9c57"
total_cost0.00012495
cache_discount(null)
upstream_inference_cost0
provider_name"Novita"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Melanie"
dialogue"Entschuldigung, ich… das ist alles zu schnell."
detectedLang"de"
heavyLang"de"
scores
de0.8360242179616549
nl0.559620596205962
no0.43771626297577854
fr0.3959107806691449
et0.36647173489278756
da0.36149312377210213
pt0.3380855397148676
it0.3298969072164949
sk0.27616926503340755
pl0.26136363636363635
ms0.2562929061784897
hi0.2459396751740139
ca0.22985781990521328
tr0.2243436754176611
es0.19753086419753088
sv0.1935483870967742
en0.17721518987341772
fi0.17721518987341772
tl0.17721518987341772
reliabletrue
passestrue
1
name"Hunter"
dialogue"Ma'am, I'm Detective Hunter. I'm looking into the recent disappearances. Did you see anything unusual at the café earlier today?"
detectedLang"en"
heavyLang"en"
scores
en0.7861097131353799
tl0.5392953929539296
fr0.5337356006582556
pt0.5248742314141979
nl0.5078170237405906
da0.4060097833682739
no0.40056417489421725
ca0.38361131254532266
ro0.38181818181818183
es0.37591776798825255
sv0.34815950920245403
it0.3161705551086082
ms0.31451612903225806
sq0.2796610169491525
cs0.2576419213973799
et0.24444444444444446
de0.22867513611615245
yo0.18582375478927202
sl0.18190567853705486
sk0.15
hr0.1326530612244898
lv0.08008658008658008
is0.07709011943539631
pl0.07508161044613709
lt0.06900328587075576
tr0.06490649064906491
reliabletrue
passestrue
2
name"Melanie"
dialogue"Ich habe nur Fotos gemacht. Aber ich hörte das laute Geräusch, als das Licht plötzlich ausging, und dann… niemand war mehr da."
detectedLang"de"
heavyLang"de"
scores
de0.8223699289479715
nl0.5804006497022198
pt0.359504132231405
en0.32842287694974004
pl0.3092691622103387
az0.29800724637681164
tr0.2688679245283019
ro0.2647058823529412
fr0.25623800383877166
is0.25480769230769235
ca0.251207729468599
ms0.24684159378036927
da0.24242424242424243
no0.2319127849355798
sv0.2288557213930348
es0.20998980632008157
tl0.20103092783505155
sk0.19772256728778467
sl0.19689119170984457
hr0.19270833333333331
fi0.18592436974789917
it0.18076109936575055
lt0.15577342047930284
lv0.1474147414741474
eu0.13793103448275862
yo0.08823529411764706
cs0.07957244655581948
et0.07517899761336516
sq0.07517899761336516
vi0.07517899761336516
reliabletrue
passestrue
3
name"Hunter"
dialogue"What do you mean 'nobody was there'?"
detectedLang"en"
heavyLang"en"
scores
en0.8191318327974276
de0.5689655172413793
cs0.5622568093385214
sk0.4827586206896552
sq0.46428571428571425
yo0.4230769230769231
pt0.4094488188976378
pl0.3885869565217392
nl0.3732590529247911
hr0.34782608695652173
sl0.34782608695652173
vi0.33035714285714285
tl0.25742574257425743
reliabletrue
passestrue
4
name"Melanie"
dialogue"Die Leute… sie waren weg, einfach so. Ich habe das Gefühl, dass etwas Schlimmes passiert ist."
detectedLang"de"
heavyLang"de"
scores
de0.84072375127421
nl0.49351701782820095
no0.37122736418511065
en0.3040089086859688
pt0.30167597765363136
da0.2799539170506913
sk0.2690058479532163
pl0.2664319248826291
fr0.25595238095238093
yo0.2550655542312277
ca0.25239234449760767
it0.24150485436893204
sv0.23873325213154686
is0.22839506172839508
tr0.2206982543640898
eu0.2028061224489796
sl0.19458762886597938
hi0.14500683994528044
vi0.1367403314917127
tl0.12342215988779803
et0.09420289855072464
ms0.09420289855072464
reliabletrue
passestrue
5
name"Hunter"
dialogue"Did anyone mention a name? Any clue, a face, a license plate?"
detectedLang"en"
heavyLang"en"
scores
en0.7924080664294187
fr0.6496496496496496
tl0.6413934426229507
ro0.6149614961496149
ca0.6004566210045662
pt0.5867768595041323
it0.5512820512820513
no0.5454545454545454
es0.5430809399477807
nl0.5084269662921348
de0.4868035190615836
da0.4760479041916168
hr0.47368421052631576
sk0.4444444444444444
sv0.41275167785234906
hu0.4006849315068493
ms0.38704028021015763
yo0.37722419928825623
cs0.36823104693140796
sq0.3670886075949367
pl0.31906614785992216
sl0.2985971943887776
fi0.29292929292929293
lt0.28716904276985744
tr0.279835390946502
lv0.2753623188405797
et0.2584745762711864
zh0.18032786885245902
is0.1764705882352941
az0.16666666666666666
eu0.16666666666666666
vi0.16666666666666666
reliabletrue
passestrue
6
name"Melanie"
dialogue"Ich… ich weiß nicht. Ich sah nur einen Mann mit einem dunklen Hut, der schnell ging, bevor das Licht ausging."
detectedLang"de"
heavyLang"de"
scores
de0.826533444351929
nl0.5454545454545454
no0.4271310724106325
da0.3648373983739837
ms0.30632630410654826
tl0.26035502958579887
ro0.22166874221668745
pt0.20986093552465232
fi0.19768934531450577
sk0.16555407209612816
pl0.15540540540540537
eu0.14850136239782016
en0.14266117969821673
cs0.13793103448275862
hu0.12342215988779803
is0.11095305832147938
sv0.11095305832147938
reliabletrue
passestrue
7
name"Hunter"
dialogue"Alright, that's helpful. If you remember anything else, call me, okay?"
detectedLang"en"
heavyLang"en"
scores
en0.7909893172317697
tl0.5351239669421488
nl0.44306930693069313
sq0.4360902255639098
no0.42820838627700125
ms0.42675159235668786
fr0.3706293706293706
yo0.36886395511921455
sv0.3571428571428572
da0.34210526315789475
de0.3382352941176471
sl0.32432432432432434
hu0.2822966507177033
fi0.27884615384615385
et0.27768860353130015
is0.2549668874172185
sk0.2214532871972318
es0.1847826086956522
pt0.16356877323420074
it0.15094339622641512
cs0.14772727272727273
reliabletrue
passestrue
8
name"Melanie"
dialogue"Ja, ich rufe Sie an, wenn mir etwas einfällt."
detectedLang"de"
heavyLang"de"
scores
de0.8284734133790738
pl0.5057660626029654
sk0.4094488188976378
sv0.3684210526315789
yo0.3603411513859275
et0.33920704845814975
fi0.33774834437086093
en0.3006993006993007
is0.2857142857142857
lv0.27710843373493976
ca0.2665036674816626
vi0.2665036674816626
eu0.25742574257425743
hr0.25
ro0.24433249370277077
da0.21052631578947367
fr0.21052631578947367
ms0.21052631578947367
sl0.21052631578947367
sq0.2
tr0.19137466307277629
reliabletrue
passestrue
9
name"Hunter"
dialogue"Excuse me, I have to take this."
detectedLang"en"
heavyLang"en"
scores
en0.7995991983967936
da0.6610169491525424
no0.6330275229357798
tl0.6303142329020333
sl0.5893223819301848
sq0.5850622406639004
pl0.5661605206073753
hr0.5604395604395604
cs0.5412844036697247
yo0.5283018867924528
sk0.504950495049505
it0.4936708860759494
lv0.4805194805194805
lt0.4550408719346049
et0.441340782122905
ca0.40828402366863903
sv0.40828402366863903
es0.33774834437086093
fr0.3127147766323024
ro0.3103448275862069
pt0.3055555555555556
ms0.29577464788732394
nl0.29577464788732394
fi0.2727272727272727
be0.25925925925925924
tr0.25925925925925924
hu0.250936329588015
az0.23954372623574144
is0.23954372623574144
uk0.23954372623574144
vi0.23954372623574144
reliabletrue
passestrue