Run: 2026-02-17-01KHNF6HDTTSFXP5RSPKZJNEWP

Run Details

Model:
Minimax M2.5
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
10.7s
Cost:
$0.001157
Provider:
Fireworks

Evaluation summary

Score Evaluator
Details Link
52.94% 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
# Scene: Cafe Encounter **Setting:** *A small café in Alborn, MN. SELVI sits at a corner table, gently turning over her camera. She looks troubled, occasionally glancing out the window. HUNTER approaches, notepad in hand.* --- Selvi: *(mumbling while looking at her camera)* "Kya hua? Ye toh... ye toh wohi jagah thi... jahan maine... jahan wo log gaye thein..." *(She shudders, gripping the camera tighter.)* Hunter: "Excuse me. Ma'am? I'm Detective Hunter. I was hoping to ask you a few questions about what happened at the orchard last week." Selvi: *(looking up, startled)* "Aap kaun hain? Kya aap mujhe baat kar rahe hain?" Hunter: *(frowning)* "I'm sorry, I don't... wait, do you speak English?" Selvi: "Main aapki baat nahin samjha. Kya aap Hindi bolte hain?" Hunter: *(looking confused, tapping his notepad)* "Uh... I don't understand what you're saying. I need to ask you about the—" *(he gestures vaguely)* "—the thing that happened. The disappearances." Selvi: *(eyes widening, speaking rapidly in Hindi)* "Haain? Log khown gaye? Nahin, nahin! Main wahan naheen gayi thi! Main bas—bas photo lo raha tha!" Hunter: *(stepping back, completely lost)* "Ma'am, I'm sorry, I really don't understand you. Do you speak any English at all?" Selvi: *(frustrated, holding up her camera)* "Camera! Camera! Main bas ye le raha tha!" Hunter: *(pointing at the camera)* "Your camera? What about it?" Selvi: *(desperately)* "Woh jagah! Woh bagh! Jahan sab kuch—jahan log—" Hunter: *(sighing, rubbing his forehead)* "Look, I don't know what you're trying to tell me, but I need to—" *(Hunter's phone rings. He glances at the screen.)* Hunter: *(answering)* "Hunter here... What? I'm at the café now—yeah, yeah, I'm coming." *(He hangs up and looks at Selvi apologetically.)* Hunter: "Look, I have to go. Something's come up. But don't leave town, alright? We'll need to talk again. With a translator or something." Selvi: *(confused)* "Translate? Kya? Aap ja rahe hain?" Hunter: "I have to go. We'll figure this out later." *(Hunter exits quickly. Selvi sits alone, looking down at her camera, clearly shaken.)* Selvi: *(quietly, to herself)* "Wo log... woh sab log... aur maine sab kuch dekha tha..." --- *END SCENE*
created_at"2026-02-17T09:34:25.113078+00:00" 2/17/2026, 9:34:25 AM
model"minimax/minimax-m2.5-20260211"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency533
moderation_latency(null)
generation_time10517
tokens_prompt315
tokens_completion935
native_tokens_prompt278
native_tokens_completion895
native_tokens_completion_images(null)
native_tokens_reasoning331
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"
usage0.0011574
router(null)
provider_responses
0
id"0e6ef51d-ad2f-4f3b-af07-9615aee27280"
status200
is_byokfalse
latency533
endpoint_id"c61d37ec-745c-4efd-8129-a68371e056b2"
provider_name"Fireworks"
model_permaslug"minimax/minimax-m2.5-20260211"
api_type"completions"
id"gen-1771320853-6FVv6L6hMlIOScT9J5wm"
upstream_id"0e6ef51d-ad2f-4f3b-af07-9615aee27280"
total_cost0.0011574
cache_discount(null)
upstream_inference_cost0
provider_name"Fireworks"

Evaluation details

Result Evaluator Details Meta Data
52.94% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Kya hua? Ye toh... ye toh wohi jagah thi... jahan maine... jahan wo log gaye thein..."
detectedLang"de"
heavyLang"de"
scores
de0.4700748129675811
en0.4370860927152318
yo0.4089012517385257
et0.3928571428571429
fi0.371301775147929
ms0.36377245508982037
tl0.3338557993730407
fr0.3285939968404423
vi0.2672413793103448
ro0.256993006993007
sv0.1904761904761905
tr0.1904761904761905
lv0.17153996101364524
reliablefalse
passesfalse
1
name"Hunter"
dialogue"Excuse me. Ma'am? I'm Detective Hunter. I was hoping to ask you a few questions about what happened at the orchard last week."
detectedLang"en"
heavyLang"en"
scores
en0.7969366442330007
tl0.6212121212121212
fr0.561623246492986
no0.5249728555917481
nl0.5189664650907091
da0.47885646217986894
it0.4728915662650602
pt0.44620253164556967
ca0.4281045751633987
sq0.4002741603838246
ro0.38162544169611307
yo0.3803116147308782
cs0.3718592964824121
sv0.36084733382030676
es0.35803374908290536
hr0.3315508021390375
de0.33103975535168195
sl0.3269230769230769
et0.29605792437650846
pl0.29492344883158744
ms0.2926434923201294
sk0.2762613730355666
lv0.22566371681415928
lt0.22153024911032027
hu0.20309653916211293
tr0.19056429232192415
fi0.1362290227048371
is0.1362290227048371
az0.13194444444444445
vi0.13194444444444445
be0.07407407407407407
eu0.07407407407407407
uk0.06716417910447761
reliabletrue
passestrue
2
name"Selvi"
dialogue"Aap kaun hain? Kya aap mujhe baat kar rahe hain?"
detectedLang"sl"
heavyLang"af"
scores
sl0.4094488188976378
eu0.38016528925619836
tr0.30769230769230765
reliablefalse
passesfalse
3
name"Hunter"
dialogue"I'm sorry, I don't... wait, do you speak English?"
detectedLang"en"
heavyLang"en"
scores
en0.8020706455542022
tl0.5206489675516224
hr0.5045731707317073
cs0.49297971918876754
pl0.45286195286195285
pt0.4406196213425129
sq0.4357638888888889
no0.411231884057971
it0.3981481481481482
da0.39365671641791045
sv0.3925233644859813
sk0.385633270321361
vi0.3486973947895792
yo0.336734693877551
ro0.33264887063655035
ca0.29805615550755943
sl0.2696629213483146
de0.181360201511335
ms0.181360201511335
be0.17721518987341772
tr0.17721518987341772
hu0.1709183673469388
az0.16237113402061853
et0.16237113402061853
is0.16237113402061853
lt0.16237113402061853
lv0.16237113402061853
uk0.16237113402061853
reliabletrue
passestrue
4
name"Selvi"
dialogue"Main aapki baat nahin samjha. Kya aap Hindi bolte hain?"
detectedLang"tl"
heavyLang"tl"
scores
tl0.5910577971646674
eu0.4318181818181818
it0.3832236842105263
is0.35121107266435986
en0.20886075949367086
et0.20042643923240938
fr0.19006479481641467
sq0.1883116883116883
de0.17218543046357618
hi0.17218543046357618
reliabletrue
passesfalse
5
name"Hunter"
dialogue"—the thing that happened. The disappearances."
detectedLang"en"
heavyLang"en"
scores
en0.8212157330154947
tl0.6113989637305699
fr0.5658465991316932
nl0.4906621392190153
ms0.45848375451263534
pt0.3492407809110629
ca0.3348115299334811
yo0.2628992628992629
no0.24050632911392408
es0.22879177377892032
it0.2248062015503876
da0.20634920634920634
sq0.20634920634920634
sv0.20634920634920634
lv0.19786096256684493
reliabletrue
passestrue
6
name"Selvi"
dialogue"Haain? Log khown gaye? Nahin, nahin! Main wahan naheen gayi thi! Main bas—bas photo lo raha tha!"
detectedLang"ms"
heavyLang"vi"
scores
ms0.460431654676259
tl0.4553941908713693
fr0.42622950819672134
en0.41666666666666663
vi0.31906614785992216
fi0.27586206896551724
de0.2584745762711864
eu0.21875
et0.21171171171171171
es0.21052631578947367
yo0.20694864048338368
it0.19230769230769232
sq0.1822429906542056
nl0.16
ca0.14772727272727273
cs0.1435562805872757
pt0.13793103448275862
hi0.12790697674418602
reliablefalse
passesfalse
7
name"Hunter"
dialogue"Ma'am, I'm sorry, I really don't understand you. Do you speak any English at all?"
detectedLang"en"
heavyLang"en"
scores
en0.7956909361069836
tl0.6060171919770774
no0.5982468955441929
da0.5756172839506173
sv0.47267497603068076
cs0.4570582428430405
pl0.4294605809128631
de0.42105263157894735
hr0.41737288135593226
sq0.4167550371155886
it0.39692982456140347
sk0.39560439560439564
ca0.3840985442329227
pt0.3820224719101124
ro0.3612078977932636
nl0.301143583227446
sl0.24965893587994542
vi0.2403314917127072
yo0.23076923076923078
et0.21540656205420827
is0.19941775836972345
ms0.19236417033773862
az0.1863905325443787
lt0.1863905325443787
lv0.1863905325443787
es0.13112164296998421
be0.11290322580645161
tr0.11290322580645161
hu0.1085899513776337
uk0.10277324632952692
reliabletrue
passestrue
8
name"Selvi"
dialogue"Camera! Camera! Main bas ye le raha tha!"
detectedLang"fr"
heavyLang"vi"
scores
fr0.6894409937888198
it0.6023856858846919
ro0.576271186440678
yo0.5525727069351231
es0.5215311004784688
en0.4666666666666667
ms0.46236559139784944
de0.42857142857142855
et0.41348973607038125
sl0.36908517350157727
sq0.36908517350157727
ca0.33774834437086093
tr0.3333333333333333
hu0.3288590604026846
sv0.2907801418439716
nl0.2753623188405797
tl0.2647058823529412
reliabletrue
passesfalse
9
name"Hunter"
dialogue"Your camera? What about it?"
detectedLang"en"
heavyLang"en"
scores
en0.8226950354609929
tl0.5635910224438903
it0.47447447447447455
ro0.47447447447447455
ms0.4615384615384615
ca0.36823104693140796
es0.3613138686131387
lv0.32950191570881227
sq0.32950191570881227
sv0.31906614785992216
fr0.3027888446215139
nl0.3027888446215139
yo0.3027888446215139
de0.29149797570850206
reliabletrue
passestrue
10
name"Selvi"
dialogue"Woh jagah! Woh bagh! Jahan sab kuch—jahan log—"
detectedLang"ms"
heavyLang"de"
scores
ms0.5192307692307693
tl0.3679775280898876
et0.33234421364985167
sv0.30769230769230765
fi0.281150159744409
reliablefalse
passesfalse
11
name"Hunter"
dialogue"Look, I don't know what you're trying to tell me, but I need to—"
detectedLang"en"
heavyLang"en"
scores
en0.8292349726775956
no0.4791666666666667
tl0.4762569832402235
et0.44196428571428575
sq0.4292237442922375
pl0.410377358490566
hr0.40476190476190477
da0.39320388349514557
cs0.3862520458265139
yo0.37395659432387307
sl0.3578767123287671
sk0.35233160621761656
it0.34210526315789475
lv0.33035714285714285
fr0.3231046931407942
lt0.3081180811808118
ca0.2690058479532163
sv0.2690058479532163
es0.21383647798742136
ro0.1935483870967742
pt0.19006479481641467
ms0.1830065359477124
nl0.1830065359477124
fi0.16666666666666666
be0.15730337078651685
tr0.15730337078651685
hu0.1515837104072398
az0.14383561643835618
is0.14383561643835618
uk0.14383561643835618
vi0.14383561643835618
reliabletrue
passestrue
12
name"Hunter"
dialogue"Hunter here... What? I'm at the café now—yeah, yeah, I'm coming."
detectedLang"en"
heavyLang"en"
scores
en0.7899159663865546
tl0.5849297573435505
nl0.5757180156657963
da0.5625841184387618
no0.5523415977961432
pt0.5234604105571847
fr0.49297971918876754
sq0.4217081850533808
de0.33264887063655035
it0.3257261410788381
ro0.3257261410788381
ca0.3200836820083682
sv0.3128964059196617
ms0.29653679653679654
yo0.2476851851851852
es0.23708920187793428
sl0.15364583333333331
tr0.15364583333333331
reliabletrue
passestrue
13
name"Hunter"
dialogue"Look, I have to go. Something's come up. But don't leave town, alright? We'll need to talk again. With a translator or something."
detectedLang"en"
heavyLang"en"
scores
en0.8015380798809228
tl0.5733333333333334
da0.4520547945205479
pl0.43302622253720763
no0.394856278366112
yo0.38176197836166925
hr0.3803253292021689
nl0.37402190923317685
it0.3675889328063241
fr0.3532740501212611
cs0.3480032599837001
sk0.3316624895572264
ro0.3277310924369748
et0.32489451476793246
pt0.3097497842968076
sq0.3061578490893322
ca0.30374238468233244
ms0.2976294995610184
sl0.2926613616268789
lv0.28698752228163993
sv0.2863514719000892
lt0.2831541218637993
es0.2640294388224471
de0.2558139534883721
hu0.2179863147605083
vi0.21645445641527913
tr0.2079207920792079
az0.1935483870967742
is0.14712153518123666
eu0.14621131270010673
be0.08045977011494253
fi0.07300115874855156
uk0.07300115874855156
reliabletrue
passestrue
14
name"Selvi"
dialogue"Translate? Kya? Aap ja rahe hain?"
detectedLang"en"
heavyLang"et"
scores
en0.5735607675906184
et0.5157384987893463
eu0.5061728395061729
ca0.4791666666666667
lv0.47643979057591623
ro0.4550408719346049
de0.43661971830985913
fi0.43342776203966005
pl0.42857142857142855
sk0.42363112391930835
sq0.42363112391930835
da0.41690962099125367
sl0.41002949852507375
hr0.40828402366863903
it0.40828402366863903
no0.40828402366863903
tl0.40828402366863903
sv0.40119760479041916
vi0.3055555555555556
fr0.2857142857142857
pt0.2857142857142857
es0.2779783393501805
yo0.2727272727272727
lt0.250936329588015
nl0.23954372623574144
tr0.23954372623574144
az0.2277992277992278
cs0.2277992277992278
ms0.2277992277992278
reliablefalse
passesfalse
15
name"Hunter"
dialogue"I have to go. We'll figure this out later."
detectedLang"en"
heavyLang"en"
scores
en0.8013245033112583
da0.6483001172332942
tl0.6300863131935881
pl0.5973154362416108
no0.5798319327731093
yo0.5008319467554077
hr0.4594594594594595
ro0.441340782122905
cs0.44029850746268656
de0.42857142857142855
sv0.42748091603053434
fr0.42084942084942084
ca0.4174757281553398
sq0.4129158512720157
nl0.4106090373280943
sk0.40476190476190477
lv0.3814432989690722
it0.38016528925619836
lt0.3576017130620985
pt0.3181818181818182
sl0.28741092636579574
hi0.20212765957446807
be0.1891891891891892
tr0.1891891891891892
es0.18699186991869918
hu0.18256130790190736
az0.17355371900826447
et0.17355371900826447
is0.17355371900826447
uk0.17355371900826447
vi0.17355371900826447
reliabletrue
passestrue
16
name"Selvi"
dialogue"Wo log... woh sab log... aur maine sab kuch dekha tha..."
detectedLang"de"
heavyLang"vi"
scores
de0.49725776965265084
ro0.47817836812144215
fr0.43064182194616984
yo0.3806306306306307
en0.3721461187214612
et0.3721461187214612
fi0.3721461187214612
sq0.298469387755102
ms0.2763157894736842
lv0.24242424242424243
tl0.22969187675070027
reliablefalse
passesfalse