NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM1FWNAB2V9HHYPMZ9QSRGV5
Run Details
Model:
MiniMax M2.7
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 19s
Cost:
$0.013980
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.19%
Dialogue to Total Word Ratio
(details)
99.5966%
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 spread the blueprints on the kitchen table. Bill squinted at the pastel invitation. "Molly: Okay, here's the plan: we crash the 'Princesses & Pirates' birthday bash, blend with the glittery mob, then snatch every present under the giant bounce house." "Bill: Do we really need to wear a superhero cape? I thought the clown disguise was the ticket." "Molly: Absolutely. The capes make us look like extra party favors, and the kids will think we’re the magical prize patrol. Plus, the parents will be too busy photographing to notice a couple of extra 'goody' smugglers." "Bill: Alright, I’m in. What’s the timing? Do we sneak in when the cake’s being cut, or wait till the piñata explodes?" "Molly: We’ll hit the moment the glitter confetti cannons fire. That’s when the parents’ eyes will be locked on the sky, not the gift table. I’ll hand you the lock‑pick, you slip the glittery ribbon off the presents." "Bill: Got it. And if anyone asks, we’re party favors delivery crew. I’ll wear a name tag that says 'Gifts, Inc.' and you can flash a badge that reads 'Chief Elf.' That should keep the kids from screaming and the cops from showing up."
created_at
"2026-03-18T22:08:35.665Z"
3/18/2026, 10:08:35 PM
model
"minimax/minimax-m2.7-20260318"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
832
moderation_latency
(null)
generation_time
199171
tokens_prompt
77
tokens_completion
11333
native_tokens_prompt
101
native_tokens_completion
11625
native_tokens_completion_images
(null)
native_tokens_reasoning
11350
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
0.0139803
router
(null)
provider_responses
0
endpoint_id
"471cf4ea-3548-4dd7-9f86-8c0f9c21d3ca"
id
"060a556354c4f76d7be5e148cc47e132"
is_byok
false
latency
832
model_permaslug
"minimax/minimax-m2.7-20260318"
provider_name
"Minimax"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773871715-0gdW4fGWYuNaiI9VVaZh"
upstream_id
"060a556354c4f76d7be5e148cc47e132"
total_cost
0.0139803
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Minimax"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.19%
Dialogue to Total Word Ratio
Ratio: 93.00%, Deviation: 3.00%
neededClean
false
wordsTotal
200
wordsDialogue
186
99.5966%