NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNFXPZ2DKCFR3Q6RYB55NR5
Run Details
Model:
Minimax M2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 28s
Cost:
$0.007940
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly and Bill crouched behind a bounce castle, scheming. They whispered. Molly: We need a disguise that screams fun uncle but hides a lock pick. Bill: I was thinking a clown nose, but maybe a superhero cape? Kids love capes. Molly: Capes are too obvious. How about a party hat that doubles as a mirror for checking exits? Bill: Perfect. We'll blend in, then swoop the presents while the parents chase the piƱata. Molly: We can't just grab the pile. We'll need a distraction maybe a magic trick? Bill: I can swallow a balloon, but the real trick is swapping the gifts with dummy boxes. Molly: Have you practiced the invisible bag move? Bill: Only in my living room. It's basically a magic bag that looks empty but holds a whole loot. Molly: Alright, we go in when the cake is cut. The lights will dim, and the parents will be busy filming. Bill: Then we slip the presents into the bag, tip the hat, and exit through the inflatable slide. Molly: And if anyone asks, we claim we are the entertainers who forgot our fee. Bill: Deal. Let's move before the clown realizes his nose is missing seriously absolutely.
created_at
"2026-02-17T09:48:21.930766+00:00"
2/17/2026, 9:48:21 AM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2942
moderation_latency
(null)
generation_time
87659
tokens_prompt
77
tokens_completion
6262
native_tokens_prompt
98
native_tokens_completion
6592
native_tokens_completion_images
(null)
native_tokens_reasoning
5963
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0079398
router
(null)
provider_responses
0
id
"130f1ff368354cbc88796e17bebc1689"
status
200
is_byok
false
latency
2942
endpoint_id
"acf82778-f331-40d9-ad3f-8c57494d4c4b"
provider_name
"AtlasCloud"
model_permaslug
"minimax/minimax-m2.5-20260211"
api_type
"completions"
id
"gen-1771321613-5K5NNCE3KeACJCFB01xJ"
upstream_id
"130f1ff368354cbc88796e17bebc1689"
total_cost
0.0079398
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
50.0000%