NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPDKY4B43CR8P4VVR0P2A7
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.3s
Cost:
$0.000644
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
6.42%
Dialogue to Total Word Ratio
(details)
43.8470%
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 adjusted her oversized clown wig and glared at Bill. “You’re telling me the *best* time to hit the piñata stash is *during* the cake?” Bill shoved a handful of balloons into his jumpsuit. “Kid’s blowing out candles, parents are distracted by sugar crashes—it’s *perfect*. We waltz in, grab the loot, and vanish before the first tantrum.” “And if some five-year-old recognizes us from the *last* birthday we hit?” “Then we improvise.” Bill grinned, pulling out a kazoo. “I’ll play ‘Happy Birthday’ off-key. You start crying about gluten. Works every time.” Molly sighed. “You realize the *real* score isn’t the My Little Ponies, right? It’s the *gift cards* in the parents’ purses.” Bill gasped, clutching his chest. “Molly. We *agreed*. No picking pockets at a *bounce house*. That’s just *rude*.” “Fine. But if I see a mom drop her wallet in the ball pit, it’s *fair game*.” “Deal.” Bill adjusted his fake mustache. “Now, remember—if anyone asks, we’re ‘Uncle Bob and Aunt Linda.’” “Why those names?” “Because no one *ever* remembers Uncle Bob.” Bill tossed her a party hat. “Let’s go ruin childhoods.”
created_at
"2026-02-20T14:14:21.391Z"
2/20/2026, 2:14:21 PM
model
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
287
moderation_latency
(null)
generation_time
5248
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
69
native_tokens_completion
308
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0006436
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"9994d6b7250c4bee8d01846f58a45536"
is_byok
false
latency
287
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771596861-oZfqrMDV9H68SKwtnhDG"
upstream_id
"9994d6b7250c4bee8d01846f58a45536"
total_cost
0.0006436
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
6.42%
Dialogue to Total Word Ratio
Ratio: 77.13%, Deviation: 12.87%
neededClean
false
wordsTotal
188
wordsDialogue
145
43.8470%