NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNEZYDB1N1NHRX4S0SA1QCZ
Run Details
Model:
Minimax M2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
20.0s
Cost:
$0.001049
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
2.63%
Dialogue to Total Word Ratio
(details)
44.5070%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Bill adjusted his fake mustache for the third time, squinting at the map spread across the hood of their rust-bucket car. The Hendersons' house glowed pink in the distance, balloons bobbing from the mailbox like festive prisoners awaiting rescue. "You sure about this?" Molly whispered, twirling a lockpick between her fingers. "We steal from a children's party." Bill nodded seriously. "Nothing personal. Just business." They crept through the hedges, Bill's knees cracking like bubble wrap. The back door was propped open by a plastic dinosaur. Molly grinned. This was almost too easy. As they approached the gift table, Bill's stomach growled loudly. A clown was doing balloon animals nearby. A child screamed about needing more pizza. The chaos was perfect. They filled their bags with wrapped presents, trying not to read the labels. One box suspiciously rattled. "LEGO," Bill whispered. "Excellent." Molly checked her watch. "Two minutes. The parents are in the backyard." Bill grinned, his fake mustache finally staying put. "To the van, darling." They tiptoed toward freedom, pillows of loot bulging beneath their coats, the sounds of celebration fading behind them like a dying radio station.
created_at
"2026-02-17T09:30:58.383552+00:00"
2/17/2026, 9:30:58 AM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1879
moderation_latency
(null)
generation_time
19966
tokens_prompt
77
tokens_completion
967
native_tokens_prompt
97
native_tokens_completion
850
native_tokens_completion_images
(null)
native_tokens_reasoning
652
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
0.0010491
router
(null)
provider_responses
0
id
"564c5d7d-ec5c-4654-8027-9ccf65a2f30b"
status
200
is_byok
false
latency
1874
endpoint_id
"c61d37ec-745c-4efd-8129-a68371e056b2"
provider_name
"Fireworks"
model_permaslug
"minimax/minimax-m2.5-20260211"
api_type
"completions"
id
"gen-1771320637-EMaNN3IgtINZhTkc3Vz3"
upstream_id
"564c5d7d-ec5c-4654-8027-9ccf65a2f30b"
total_cost
0.0010491
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Fireworks"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
2.63%
Dialogue to Total Word Ratio
Ratio: 23.81%, Deviation: 13.81%
neededClean
false
wordsTotal
189
wordsDialogue
45
44.5070%