Run: 2026-03-03-01KJTZX7BN49A5FJCX06JYJ12A

Run Details

Model:
ByteDance Seed 2.0 Mini
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
3m 36s
Cost:
$0.003098
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
60.00% 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="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
### Voice Sheet **[Alborn, MN Corner Café – Mid-Morning]** Hunter: (leaning forward, professional but warm, speaking clear English) Good morning. I’m Detective Hunter with the Alborn Sheriff’s Department. I’m investigating the recent disappearance of local apple farmer Hank Forrester. Did you happen to see anything out of the ordinary near his orchard over the past week? Selvi: (jumps slightly, then rambles in rapid, shaken Hindi—unintelligible to Hunter) Oh thank goodness you asked! I saw him— a man in a black hoodie loading crates of apples into a beat-up gray pickup behind Hank’s shed last Tuesday at sunset. I was taking photos of the orchards and he spotted me, so I hid until he drove away. I didn’t report it sooner because I’m a foreign student here, I thought no one would listen to me! Hunter: (furrows his brow, eyes wide with total confusion, waving a hand to calm her) Wait, hold on. I don’t understand what you’re saying. I can’t follow any of this. I don’t speak any Hindi at all. Selvi: (freezes, voice cracking as she repeats her plea in faster, more urgent Hindi) But I saw him! I have the photo on my camera! He’s the one who took Hank! I swear it’s true! Hunter: (rubbing the back of his neck, flustered by the total language barrier, gestures weakly to her camera) I wish I could help, but I don’t understand a single word of your language. Can you show me the photo you mentioned? Please? Selvi: (fumbles with her camera, taps the screen until a grainy shot of a shadowy pickup behind an apple shed pops up, holds the device out) Look, please. Hunter: (leans in to squint at the photo, nodding as he recognizes the shed behind Hank’s stand) Alright, I see that. That’s the back of Hank’s property. Look, I hate to cut this short— [Hunter’s phone buzzes loudly in his pocket] Hunter: (fumbles to answer, listens for 10 seconds before slamming his notebook shut) Alright, I’m on my way. (hangs up, tears a slip of paper with his direct line and shoves it across the table) I just got a new missing person report— I have to go. Take this, if you can find someone to translate what you told me, call that number. Selvi: (stares at the slip of paper, muttering in quiet, defeated Hindi) What am I supposed to do now? Hunter: (yelling over his shoulder as he bolts for the door) Find someone who speaks both languages! Call that number!
created_at"2026-03-03T23:18:19.862Z" 3/3/2026, 11:18:19 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency725
moderation_latency(null)
generation_time205028
tokens_prompt315
tokens_completion8253
native_tokens_prompt324
native_tokens_completion7664
native_tokens_completion_images(null)
native_tokens_reasoning7074
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"
usage0.003098
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"0217725798999739953a9193bc3926b190298875f636f3e8d6ce9"
is_byokfalse
latency725
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772579899-A04GG0BOprwPvSC8oN1G"
upstream_id"0217725798999739953a9193bc3926b190298875f636f3e8d6ce9"
total_cost0.003098
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
60.00% Parse dialogue n/a
dialogue
0
name"Hunter"
dialogue"Good morning. I’m Detective Hunter with the Alborn Sheriff’s Department. I’m investigating the recent disappearance of local apple farmer Hank Forrester. Did you happen to see anything out of the ordinary near his orchard over the past week?"
detectedLang"en"
heavyLang"en"
scores
en0.7856154910096819
tl0.6533989266547406
nl0.5443856554967665
fr0.5169834839513867
no0.5073108709472346
ro0.4751100575685744
da0.4713506139154161
sv0.44879089615931717
it0.43860919956537486
de0.4341000365096751
pt0.42909760589318596
es0.38686708860759494
ca0.38049560351718625
cs0.34791754312158185
sq0.3409863945578231
hr0.3361884368308351
ms0.30957683741648107
sk0.3067978533094812
sl0.2941712204007286
is0.23682914820285572
yo0.23607688516510594
et0.22847187655550022
lt0.21677614957049016
pl0.17902542372881353
hu0.1702355460385439
az0.1388888888888889
lv0.11021814006888633
tr0.07296650717703348
eu0.049079754601226995
fi0.036668738346799255
reliabletrue
passestrue
1
name"Selvi"
dialogue"Oh thank goodness you asked! I saw him— a man in a black hoodie loading crates of apples into a beat-up gray pickup behind Hank’s shed last Tuesday at sunset. I was taking photos of the orchards and he spotted me, so I hid until he drove away. I didn’t report it sooner because I’m a foreign student here, I thought no one would listen to me!"
detectedLang"en"
heavyLang"en"
scores
en0.7829198473282443
tl0.6085684790089471
no0.4855269109000452
nl0.44430874450415236
da0.4407571288102262
de0.42156114924993643
fr0.39558979808714134
sv0.3634583100167879
yo0.3475767135073129
pl0.3255262377705307
sk0.30724725943970765
es0.3027888446215139
ca0.29501084598698485
sq0.29457364341085274
cs0.2934782608695652
it0.2850408548082967
et0.28414096916299564
lv0.2793791574279379
pt0.2780069819105046
sl0.27246562200191876
hr0.27059955113818535
ro0.2639922355224847
fi0.2160578911095796
tr0.20869565217391306
ms0.198943661971831
is0.18952618453865336
lt0.178106936416185
hu0.15865384615384615
vi0.14215686274509806
eu0.1260084517864003
az0.11375146084924037
hi0.03273809523809524
be0.029850746268656716
uk0.026946107784431135
reliabletrue
passesfalse
2
name"Hunter"
dialogue"Wait, hold on. I don’t understand what you’re saying. I can’t follow any of this. I don’t speak any Hindi at all."
detectedLang"en"
heavyLang"en"
scores
en0.8182063021815242
tl0.6951219512195121
no0.5335176226675881
da0.5185449358059915
sv0.3841240875912409
et0.3715083798882682
ca0.35406698564593303
it0.3522072936660269
de0.3401759530791789
is0.32432432432432434
nl0.3105209397344229
sq0.30268595041322316
pl0.29906542056074764
yo0.2894736842105263
cs0.281150159744409
sk0.25905598243688255
hr0.2516629711751663
tr0.20118343195266272
ro0.19547079856972585
hi0.1935483870967742
fi0.1818181818181818
fr0.13903061224489796
be0.09395973154362416
hu0.09029649595687331
az0.08536585365853659
lt0.08536585365853659
lv0.08536585365853659
uk0.08536585365853659
vi0.08536585365853659
reliabletrue
passestrue
3
name"Selvi"
dialogue"But I saw him! I have the photo on my camera! He’s the one who took Hank! I swear it’s true!"
detectedLang"en"
heavyLang"en"
scores
en0.8015156983038614
tl0.609652235628105
fr0.4958753437213565
pl0.4142705005324814
da0.3982494529540482
cs0.39159292035398224
ca0.3813273340832396
hr0.36342592592592593
sv0.3514150943396226
it0.33171324422843257
yo0.32844932844932845
nl0.32014833127317677
ms0.3125
ro0.31077694235588976
no0.3037974683544304
sk0.29757343550446996
et0.28292046936114734
sq0.27821522309711283
hi0.22644163150492264
fi0.21428571428571427
es0.15254237288135594
de0.11575562700964631
be0.11290322580645161
tr0.11290322580645161
hu0.1085899513776337
az0.10277324632952692
is0.10277324632952692
lt0.10277324632952692
lv0.10277324632952692
uk0.10277324632952692
vi0.10277324632952692
reliabletrue
passesfalse
4
name"Hunter"
dialogue"I wish I could help, but I don’t understand a single word of your language. Can you show me the photo you mentioned? Please?"
detectedLang"en"
heavyLang"en"
scores
en0.8226950354609929
tl0.6464869642068052
no0.55995599559956
fr0.553322166387493
nl0.51278928136419
ro0.5098039215686274
da0.50920245398773
sv0.4490358126721763
de0.4265232974910394
ca0.41690962099125367
ms0.4164843180160467
it0.40476190476190477
yo0.37936384794414274
cs0.37839937839937837
sq0.35064935064935066
is0.32489451476793246
pt0.3162393162393162
es0.313893653516295
sk0.3103448275862069
hr0.2831541218637993
pl0.27862939585211904
hu0.27338782924613986
et0.27206551410373064
tr0.21875
az0.2079207920792079
lt0.20634920634920634
fi0.20398009950248755
sl0.18200408997955012
eu0.15611814345991562
lv0.14255091103965703
vi0.14255091103965703
hi0.08779931584948689
be0.08045977011494253
uk0.07300115874855156
reliabletrue
passestrue
5
name"Selvi"
dialogue"Look, please."
detectedLang"en"
heavyLang"en"
scores
en0.8344370860927153
ro0.5714285714285714
tl0.5714285714285714
reliabletrue
passesfalse
6
name"Hunter"
dialogue"Alright, I see that. That’s the back of Hank’s property. Look, I hate to cut this short—"
detectedLang"en"
heavyLang"en"
scores
en0.8134328358208955
tl0.6463714637146372
no0.5055889939810835
da0.4772727272727273
yo0.4739249771271729
et0.4460500963391137
it0.3947368421052632
sq0.3947368421052632
pl0.36323366555924697
hr0.3611111111111111
nl0.3495475113122172
cs0.3473325766174802
ro0.3290548424737456
sv0.3235294117647059
lv0.3154761904761905
sk0.31384248210023863
lt0.29274292742927427
fr0.29012345679012347
ca0.28035043804755944
sl0.23841059602649006
ms0.21555252387448842
de0.2144808743169399
is0.20907840440165062
az0.1991643454038997
fi0.1843971631205674
es0.1248097412480974
pt0.12213740458015267
eu0.11128284389489954
be0.10852713178294573
tr0.10852713178294573
hu0.1043613707165109
uk0.0987460815047022
vi0.0987460815047022
reliabletrue
passestrue
7
name"Hunter"
dialogue"Alright, I’m on my way. I just got a new missing person report— I have to go. Take this, if you can find someone to translate what you told me, call that number."
detectedLang"en"
heavyLang"en"
scores
en0.8198447893569845
tl0.658493870402802
da0.5496535796766744
no0.5257782101167315
sv0.5075757575757576
cs0.48412698412698413
et0.47297297297297297
pl0.4645799011532125
fr0.46369636963696376
ca0.46251378169790525
sk0.4500846023688663
hr0.44126074498567336
it0.43148688046647227
yo0.427144535840188
sq0.41511697660467906
nl0.41476590636254507
ro0.411231884057971
pt0.40403422982885084
de0.3925233644859813
ms0.3875628140703518
sl0.3875628140703518
es0.3644067796610169
is0.3416610398379473
hu0.3119266055045872
lv0.2893586005830903
az0.2872807017543859
lt0.2846661775495231
fi0.27293064876957496
tr0.26636568848758463
vi0.1847826086956522
eu0.12320143884892087
hi0.07932011331444759
be0.06698564593301436
uk0.06069364161849711
reliabletrue
passestrue
8
name"Selvi"
dialogue"What am I supposed to do now?"
detectedLang"en"
heavyLang"en"
scores
en0.8324646314221892
pl0.6422893481717011
hr0.625
cs0.6212121212121212
sk0.5989304812834225
no0.5916515426497277
da0.5833333333333334
yo0.5730550284629982
sq0.5273109243697479
tl0.5212765957446809
sl0.5171673819742489
ro0.4955156950672646
sv0.4827586206896552
fr0.47058823529411764
it0.4538834951456311
lv0.45121951219512196
vi0.4360902255639098
lt0.4260204081632653
pt0.4094488188976378
ca0.38016528925619836
de0.3679775280898876
hi0.27884615384615385
nl0.24242424242424243
be0.23728813559322032
tr0.23728813559322032
hu0.22945205479452058
az0.21875
et0.21875
is0.21875
uk0.21875
reliabletrue
passesfalse
9
name"Hunter"
dialogue"Find someone who speaks both languages! Call that number!"
detectedLang"en"
heavyLang"en"
scores
en0.8252621068397404
tl0.5430809399477807
et0.5159059474412172
da0.5014245014245015
ro0.43548387096774194
nl0.42148760330578516
de0.4057724957555179
no0.3383742911153119
ms0.3371212121212121
fr0.33078393881453155
is0.3217054263565891
yo0.3110236220472441
hu0.20273348519362186
es0.1822429906542056
eu0.1822429906542056
pt0.1822429906542056
sv0.1822429906542056
ca0.17452830188679244
lt0.15254237288135594
sk0.15254237288135594
sl0.15254237288135594
reliabletrue
passestrue