Run: 2026-02-16-01KHK1HAQ4F27Z14FPW5SSETPC

Run Details

Model:
Qwen 3.5 397B A17B
Test:
Language Writing
Scenario:
Character dialogue (Italian) in a story
Duration:
1m 24s
Cost:
$0.011246
Provider:
Alibaba

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

Model response

AI
Isabella: "Non parlo inglese. Per favore, lasciatemi stare." Hunter: "Do you understand me? English? Yes or no?" Isabella: "Sono italiana. Non capisco le sue parole. Sono turbata." Hunter: "Okay, look at me. That camera. Did you take pictures near the orchard yesterday?" Isabella: "La fotografia... sì. Ho visto qualcosa nel bosco. Qualcosa di brutto." Hunter: "Photos? You saw something? Can you show me?" Isabella: "Non posso! Ho paura. C'era un uomo... lui ha visto me." Hunter: "A man? Did he hurt someone? Is this about the disappearances?" Isabella: "Non lo so! Non parlo la sua lingua! Perché non mi capisce?" Hunter: "Hold on. Yeah, this is Hunter. I'm at the cafe. No, I don't have anything solid yet." Hunter: "I have to go. But I'll be back. Don't leave town." Isabella: "Andate via! Per favore, andate via!"
created_at"2026-02-16T10:58:23.191716+00:00" 2/16/2026, 10:58:23 AM
model"qwen/qwen3.5-397b-a17b-20260216"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency788
moderation_latency(null)
generation_time83944
tokens_prompt321
tokens_completion3192
native_tokens_prompt300
native_tokens_completion3074
native_tokens_completion_images(null)
native_tokens_reasoning2830
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"
usage0.0112464
router(null)
provider_responses
0
id"chatcmpl-6bbec06b-fd75-9c94-b6f9-a95c12a73c87"
status200
is_byokfalse
latency788
endpoint_id"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name"Alibaba"
model_permaslug"qwen/qwen3.5-397b-a17b-20260216"
api_type"completions"
id"gen-1771239418-nx9PVih7W7oKpCtAfjc8"
upstream_id"chatcmpl-6bbec06b-fd75-9c94-b6f9-a95c12a73c87"
total_cost0.0112464
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Isabella"
dialogue"Non parlo inglese. Per favore, lasciatemi stare."
detectedLang"it"
heavyLang"it"
scores
it0.8042168674698795
sq0.5729303547963206
es0.5554035567715458
ro0.5511049723756907
sv0.5498614958448753
en0.5467224546722455
ca0.5454545454545454
fr0.5409604519774012
sl0.5248538011695907
lt0.4897959183673469
pt0.4749596122778676
nl0.4706840390879479
no0.4663382594417077
hr0.40909090909090906
sk0.4080145719489982
de0.4036697247706422
lv0.39138576779026213
et0.37977099236641226
da0.3737957610789981
tr0.3186582809224318
az0.3114406779661017
pl0.30851063829787234
cs0.3055555555555556
yo0.2696629213483146
eu0.2111650485436893
is0.2111650485436893
hu0.1709183673469388
ms0.16237113402061853
tl0.16237113402061853
reliabletrue
passestrue
1
name"Hunter"
dialogue"Do you understand me? English? Yes or no?"
detectedLang"en"
heavyLang"en"
scores
en0.8098201936376211
no0.6733966745843231
pt0.5814307458143074
da0.5756172839506173
tl0.5346869712351946
sk0.5315161839863715
pl0.5183887915936953
cs0.5175438596491229
hr0.5158450704225351
sv0.507168458781362
de0.4907407407407407
sq0.4907407407407407
nl0.4878957169459963
es0.4649805447470817
sl0.43064182194616984
fr0.3806306306306307
it0.367816091954023
ms0.36194895591647336
ro0.34679334916864607
ca0.32926829268292684
lv0.3226600985221675
vi0.28756476683937826
et0.25675675675675674
tr0.24242424242424243
yo0.22096317280453256
fi0.21428571428571427
is0.21203438395415475
reliabletrue
passestrue
2
name"Isabella"
dialogue"Sono italiana. Non capisco le sue parole. Sono turbata."
detectedLang"it"
heavyLang"it"
scores
it0.7932569974554707
fr0.6467391304347825
es0.6140142517814726
pt0.5927318295739349
ro0.5849297573435505
en0.4873817034700315
yo0.4519392917369309
lt0.45101351351351354
sq0.41441441441441446
nl0.4080145719489982
sl0.365234375
ca0.33264887063655035
tl0.3128964059196617
cs0.2919389978213508
hr0.2919389978213508
hu0.2316784869976359
eu0.2111650485436893
pl0.19753086419753088
sk0.1792929292929293
de0.16237113402061853
no0.16237113402061853
az0.15364583333333331
da0.15364583333333331
fi0.15364583333333331
ms0.15364583333333331
sv0.15364583333333331
tr0.15364583333333331
reliabletrue
passestrue
3
name"Hunter"
dialogue"Okay, look at me. That camera. Did you take pictures near the orchard yesterday?"
detectedLang"en"
heavyLang"en"
scores
en0.788045782111064
tl0.656121045392022
nl0.5145631067961165
fr0.5059288537549407
no0.49341438703140833
da0.3939393939393939
ro0.38271604938271603
ca0.35233160621761656
it0.32249322493224936
ms0.31880108991825606
sv0.3169398907103825
sq0.3112947658402204
de0.3045897079276773
es0.2867332382310985
et0.2784992784992785
sl0.2492492492492493
yo0.17627677100494232
pt0.14965986394557826
lv0.1423670668953688
cs0.13494809688581316
fi0.13043478260869565
reliabletrue
passestrue
4
name"Isabella"
dialogue"La fotografia... sì. Ho visto qualcosa nel bosco. Qualcosa di brutto."
detectedLang"it"
heavyLang"it"
scores
it0.8172828890799657
ca0.6407438715131022
pt0.5324532453245324
no0.5272525027808677
es0.5224719101123595
fr0.4817073170731707
yo0.4798041615667074
sk0.42411924119241196
sq0.4186046511627907
sl0.41379310344827586
de0.4014084507042254
ro0.39801699716713884
tl0.3813682678311499
cs0.3609022556390977
ms0.3441358024691358
lt0.3348982785602504
nl0.32
lv0.3134087237479806
sv0.3122977346278317
da0.3089430894308943
vi0.29867986798679863
en0.2608695652173913
hr0.24377224199288253
tr0.2328519855595668
et0.22303473491773307
pl0.22303473491773307
fi0.17153996101364524
is0.1448692152917505
az0.121900826446281
reliabletrue
passestrue
5
name"Hunter"
dialogue"Photos? You saw something? Can you show me?"
detectedLang"en"
heavyLang"en"
scores
en0.8085758039816233
tl0.5840266222961731
pt0.5636998254799301
fr0.5219885277246654
ms0.51171875
es0.5098039215686274
nl0.4813278008298755
ca0.3718592964824121
sq0.3718592964824121
et0.2753623188405797
no0.2668621700879765
sl0.26035502958579887
it0.24242424242424243
lt0.24242424242424243
cs0.2378048780487805
az0.23547400611620795
hi0.23547400611620795
tr0.23547400611620795
fi0.23076923076923078
de0.22118380062305293
lv0.22118380062305293
reliabletrue
passestrue
6
name"Isabella"
dialogue"Non posso! Ho paura. C'era un uomo... lui ha visto me."
detectedLang"it"
heavyLang"it"
scores
it0.8197981739548293
ca0.6181262729124236
fr0.6006389776357828
es0.5985010706638115
pt0.5753114382785957
no0.5161290322580645
en0.42835365853658536
ro0.4221879815100154
lv0.3892508143322475
sk0.32795698924731176
sl0.3194192377495462
fi0.3029739776951673
sq0.2829827915869981
hu0.2454728370221328
sv0.24089068825910928
cs0.2203742203742204
yo0.2203742203742204
et0.20212765957446807
lt0.19006479481641467
eu0.1883116883116883
ms0.1830065359477124
nl0.1830065359477124
da0.1610738255033557
is0.1610738255033557
tl0.1610738255033557
reliabletrue
passestrue
7
name"Hunter"
dialogue"A man? Did he hurt someone? Is this about the disappearances?"
detectedLang"en"
heavyLang"en"
scores
en0.8192258613356018
tl0.5512143611404435
nl0.5493107104984093
fr0.5444801714898178
yo0.5131729667812142
es0.47400990099009904
pt0.4713930348258706
ca0.47073474470734744
hu0.42176870748299317
da0.3963068181818182
sv0.38672438672438675
no0.3786549707602339
lv0.3722304283604136
ms0.35993975903614456
it0.3328100470957614
de0.30098684210526316
lt0.2928452579034942
is0.28209459459459457
fi0.2659758203799654
sq0.2608695652173913
ro0.24645390070921988
cs0.236983842010772
sk0.23423423423423423
hr0.2085661080074488
pl0.19811320754716982
sl0.17475728155339806
tr0.1533864541832669
az0.1414141414141414
eu0.1414141414141414
vi0.1414141414141414
et0.1290983606557377
reliabletrue
passestrue
8
name"Isabella"
dialogue"Non lo so! Non parlo la sua lingua! Perché non mi capisce?"
detectedLang"it"
heavyLang"it"
scores
it0.8080087767416345
fr0.6815286624203821
es0.6791934005499541
ro0.645748987854251
ca0.6453900709219859
pt0.631578947368421
yo0.5586380832282472
en0.5530012771392081
sk0.5042492917847025
tl0.4971264367816092
sl0.4664634146341463
vi0.43910256410256415
hu0.4006849315068493
no0.39759036144578314
ms0.39130434782608703
cs0.38917975567190227
sq0.37050359712230213
de0.34579439252336447
pl0.29292929292929293
hr0.28716904276985744
tr0.2723492723492723
eu0.19908466819221968
az0.16666666666666666
et0.15254237288135594
lt0.15254237288135594
nl0.15254237288135594
da0.14425427872860636
lv0.14425427872860636
sv0.14425427872860636
reliabletrue
passestrue
9
name"Hunter"
dialogue"Hold on. Yeah, this is Hunter. I'm at the cafe. No, I don't have anything solid yet."
detectedLang"en"
heavyLang"en"
scores
en0.8139377537212449
tl0.6023138105567607
da0.5901639344262295
no0.533106960950764
ca0.4731800766283525
yo0.4142705005324814
hr0.4130202774813233
sq0.4028230184581976
pl0.38478747203579416
it0.37142857142857144
fr0.3692660550458715
nl0.3574766355140187
sv0.34210526315789475
pt0.3276283618581907
lv0.3150684931506849
sk0.30203045685279184
hu0.28664072632944226
et0.28292046936114734
tr0.28292046936114734
ro0.2819843342036553
ms0.28104575163398693
es0.27055702917771884
cs0.24657534246575344
is0.2198581560283688
fi0.21428571428571427
de0.2109038737446198
lt0.18154761904761904
sl0.17664670658682635
hi0.13249211356466878
be0.11290322580645161
az0.10277324632952692
uk0.10277324632952692
vi0.10277324632952692
reliabletrue
passestrue
10
name"Hunter"
dialogue"I have to go. But I'll be back. Don't leave town."
detectedLang"en"
heavyLang"en"
scores
en0.8225982532751093
tl0.5625841184387618
yo0.5584239130434783
da0.5454545454545454
pl0.531700288184438
lt0.4619205298013245
hr0.43965517241379315
no0.43868739205526774
cs0.4206773618538324
sk0.385633270321361
lv0.36274509803921573
hu0.36149312377210213
ca0.29805615550755943
sv0.29805615550755943
sq0.2919389978213508
sl0.2713004484304933
it0.26136363636363635
ro0.21686746987951808
fr0.21307506053268765
be0.17721518987341772
tr0.17721518987341772
az0.16237113402061853
et0.16237113402061853
is0.16237113402061853
uk0.16237113402061853
vi0.16237113402061853
reliabletrue
passestrue
11
name"Isabella"
dialogue"Andate via! Per favore, andate via!"
detectedLang"it"
heavyLang"it"
scores
it0.7972972972972973
ca0.719626168224299
en0.6753246753246753
nl0.6221662468513854
sv0.6113989637305699
pt0.6052631578947368
no0.5901639344262295
sl0.5901639344262295
sq0.5145631067961165
es0.5081967213114754
ro0.5081967213114754
de0.506578947368421
fr0.48805460750853247
da0.4755244755244755
lt0.44029850746268656
hr0.3670886075949367
sk0.33920704845814975
et0.33035714285714285
tl0.33035714285714285
reliabletrue
passestrue