NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQA50ZJVCRPH3WNKH2QP2Y
Run Details
Model:
Mistral Small 3.2 24B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.9s
Cost:
$0.000097
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
9.61%
Matches word count
(details)
99.47%
Dialogue to Total Word Ratio
(details)
54.5404%
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:** "Bill, I’ve got the perfect score. A children’s birthday party. No security, no alarms, just a room full of presents." **Bill:** "Molly, that’s diabolical. And by diabolical, I mean brilliant. But how do we get in without looking suspicious?" **Molly:** "Easy. We dress up as clowns. Who questions a clown?" **Bill:** "Oh, I don’t know, maybe the parents who remember the last time a clown stole their kid’s toys?" **Molly:** "Relax, we’ll be the *good* clowns. The ones who hand out balloons and make balloon animals. Then, when everyone’s distracted, we swap the presents with our duplicates." **Bill:** "Duplicates? You mean we’re bringing fake presents?" **Molly:** "No, we’re bringing *empty* presents. Kids won’t even notice until they open them. By then, we’re long gone." **Bill:** "Genius. But what if the kid cries?" **Molly:** "Then we blame the other clown. The *bad* one." **Bill:** "We’re the bad ones, Molly." **Molly:** "Semantics. You in or out?" **Bill:** "In. But if I have to wear a rainbow wig, I’m charging extra." **Molly:** "Deal. Now let’s go steal some childhood joy."
created_at
"2026-02-20T14:29:56.394Z"
2/20/2026, 2:29:56 PM
model
"mistralai/mistral-small-3.2-24b-instruct-2506"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
507
moderation_latency
(null)
generation_time
4653
tokens_prompt
77
tokens_completion
308
native_tokens_prompt
69
native_tokens_completion
302
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
0.0000975
router
(null)
provider_responses
0
endpoint_id
"23fd6b91-74d8-45fc-ac00-cf141ec7f4a5"
id
"1f3d239e10ee45ccb1b12c2fca52906c"
is_byok
false
latency
507
model_permaslug
"mistralai/mistral-small-3.2-24b-instruct-2506"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597796-iXwm8emyvcz0RsBDtcDC"
upstream_id
"1f3d239e10ee45ccb1b12c2fca52906c"
total_cost
0.0000975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
9.61%
Matches word count
n/a
neededClean
false
words
178
99.47%
Dialogue to Total Word Ratio
Ratio: 92.70%, Deviation: 2.70%
neededClean
false
wordsTotal
178
wordsDialogue
165
54.5404%