NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM1GH1E604K2P70E208EYPP7
Run Details
Model:
MiniMax M2.7
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 13s
Cost:
$0.008508
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
95.89%
Dialogue to Total Word Ratio
(details)
97.9424%
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: "Okay, listen up. We’ve got the venue—Mrs. Patterson’s backyard, bouncy castle, and a piñata that’s basically a jackpot of loot." Bill: "I love a good piñata, but I’m more worried about the security guard in the Spiderman costume. He’s got a badge and everything." Molly: "Badge, shmadge. I’ve got a fake ID that says ‘Chief of Party Supplies.’ He’ll think we’re VIPs." Bill: "And the kids? They’ll be on a sugar high, bouncing around, so we’ve got a distraction in place." Molly: "Exactly. I’ll start a bubble machine near the cake, Bill triggers the confetti cannon at the exact moment the cake’s cut." Bill: "We’ll swoop in, fill the giant sack, and roll out quickly before the clown notices." Molly: "The clown’s got a key to the gift room, right? That’s our ticket." Bill: "He does, and I’ve got a spare keychain shaped like a rubber duck. It’s a copy, just in case." Molly: "Perfect. When music swells, we scoop every present, and leave a thank‑you note signed ‘The Generous Grinches.’" Bill: "If anyone asks, we’re the surprise entertainers. The kids will think it’s magic!" Molly: "If caught, we’ll blame the birthday dad. He’s always bragging about his security."
created_at
"2026-03-18T22:19:43.436Z"
3/18/2026, 10:19:43 PM
model
"minimax/minimax-m2.7-20260318"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1462
moderation_latency
(null)
generation_time
132512
tokens_prompt
77
tokens_completion
5816
native_tokens_prompt
101
native_tokens_completion
7065
native_tokens_completion_images
(null)
native_tokens_reasoning
6751
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
0.0085083
router
(null)
provider_responses
0
endpoint_id
"471cf4ea-3548-4dd7-9f86-8c0f9c21d3ca"
id
"060a57ffe041619628f78c15c64ded1b"
is_byok
false
latency
1462
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-1773872383-haFrHSWtZbxcorFclKNo"
upstream_id
"060a57ffe041619628f78c15c64ded1b"
total_cost
0.0085083
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
201
95.89%
Dialogue to Total Word Ratio
Ratio: 94.53%, Deviation: 4.53%
neededClean
false
wordsTotal
201
wordsDialogue
190
97.9424%