NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNETWHZCABZZCQDFW8N7QCN
Run Details
Model:
Minimax M2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.2s
Cost:
$0.000486
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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
Molly crouched behind a plastic castle, her eyes tracking the bouncy castle where a dozen children screamed with sugar-fueled joy. Across the yard, Bill pretended to admire the balloon arch while actually studying the gift table like a general surveying enemy territory. "Three guards by the cake," Molly whispered into her walkie-talkie, though it was just a kids' toy she'd stolen from a dollar store. "The clown is distracted. Now's our chance." Bill adjusted his fake mustache, which was slowly peeling at the corner. "I'm telling you, the ventilation system is our ticket. I saw a schematic in the garbage last week." "You stole their garbage?" "Recycling. And yes. There's a service entrance behind the clown car. I'll handle the entertainment, you grab the loot." "What about the kids?" Bill stared at her blankly. "What about them?" Molly sighed, pulling out a crumpled note. "Your grandmother's birthday is in there somewhere. We need one specific gift, not all of them." "Fine. One gift. But I'm taking the goodie bags on the way out." They high-fived, their plan cemented. The real heist was about to begin, and nothing would stop them from retrieving that vintage watch from the pile of wrapped presents.
created_at
"2026-02-17T09:27:59.087734+00:00"
2/17/2026, 9:27:59 AM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
637
moderation_latency
(null)
generation_time
6096
tokens_prompt
77
tokens_completion
444
native_tokens_prompt
97
native_tokens_completion
381
native_tokens_completion_images
(null)
native_tokens_reasoning
124
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
0.0004863
router
(null)
provider_responses
0
id
"bd5d45df-2404-4c3b-9043-2d5c4f4b08bc"
status
200
is_byok
false
latency
637
endpoint_id
"c61d37ec-745c-4efd-8129-a68371e056b2"
provider_name
"Fireworks"
model_permaslug
"minimax/minimax-m2.5-20260211"
api_type
"completions"
id
"gen-1771320472-i1KlSUoonk2AaCwyTI56"
upstream_id
"bd5d45df-2404-4c3b-9043-2d5c4f4b08bc"
total_cost
0.0004863
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Fireworks"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
0.00%
Dialogue to Total Word Ratio
Ratio: 47.55%, Deviation: 37.55%
neededClean
false
wordsTotal
204
wordsDialogue
97
49.8722%