NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNG2634QK3KRA7T9K02T59E
Run Details
Model:
Minimax M2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 45s
Cost:
$0.009435
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9917%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 spread a blueprint on the table, the community hall glowing under a streetlamp. Balloons bobbed outside the entrance, and a sign declared a birthday celebration for a six‑year‑old. The scent of frosting drifted through a cracked pane, mixing with the faint hum of a music box. Bill traced a finger along the schedule: cake cutting at three, followed by an exodus to a bouncy castle. Their eyes met, and an agreement formed. They would disguise themselves as a clown and a magician, slip in during the distraction, and clear every wrapped gift before the parents realized anything was missing. "Molly: Alright, here's the scheme. Bill: I'm listening. Molly: We pose as the clown and the magician, get past the entrance, and when the cake is cut, the kids will rush the bouncy castle. Bill: While they bounce, I’ll distract the parents with a rabbit-from-hat trick. Molly: I’ll snatch the pile of presents, stash them in a hidden crate, and we’ll slip out the side door before anyone yells 'thief.' Bill: Perfect, we’ll vanish like birthday candles. Bill: Remember, the quicker we exit, the sooner we celebrate with pizza and a victory dance in the van. Molly: Got it, partner."
created_at
"2026-02-17T09:51:05.550329+00:00"
2/17/2026, 9:51:05 AM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
748
moderation_latency
(null)
generation_time
104939
tokens_prompt
77
tokens_completion
8808
native_tokens_prompt
98
native_tokens_completion
7838
native_tokens_completion_images
(null)
native_tokens_reasoning
8506
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
0.009435
router
(null)
provider_responses
0
id
"cdfd5306e9d345b491e96c65c2f7598e"
status
200
is_byok
false
latency
748
endpoint_id
"acf82778-f331-40d9-ad3f-8c57494d4c4b"
provider_name
"AtlasCloud"
model_permaslug
"minimax/minimax-m2.5-20260211"
api_type
"completions"
id
"gen-1771321759-U3qktsTNeQIRN1DxLFXK"
upstream_id
"cdfd5306e9d345b491e96c65c2f7598e"
total_cost
0.009435
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
100.00%
Dialogue to Total Word Ratio
Ratio: 50.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
102
99.9917%