NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM082PSJ0T6A4G8XG0CNQ844
Run Details
Model:
Mistral Small 4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
33.5s
Cost:
$0.003627
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
48.8138%
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: So, the party’s at the park, presents inside the community center. We go in, we go out, no one’s the wiser. Bill: No one’s the wiser? Molly, we’re wearing ski masks in July! Molly: Relax. We’re in disguise. I’m an auntie with two left feet. You’re my shy nephew. Hold the bag, look pathetic. Bill: And when someone asks why I’m holding the present bag? Molly: Hug it tight. Classic Nephew. Bill: And my indoor sunglasses? Molly: Allergies. Very convincing. Bill: I have those. Molly: Perfect. Grab the bag. We go in at 3:07. Juggling clown’s our distraction. Bill: Juggling clowns? You picked the worst possible distraction. Molly: Trust me, no one sees us when raccoons crash the party. Bill: Live raccoons? We’re stealing from kids! Molly: Exactly. Two raccoons blend right in. Now move, Nephew. Bill: Last job we stole a piñata. It exploded on us. Molly: Faulty piñata. And your idea to hug it tight. Bill: Had sparklers! Thought it’d be festive! Molly: Relax. In, out, before the cake’s even cut. Bill: What if we’re caught? Molly: Cry allergies. Works every time. Bill: But— Molly: Now you do. For justice.
created_at
"2026-03-18T10:32:50.752Z"
3/18/2026, 10:32:50 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
384
moderation_latency
(null)
generation_time
33376
tokens_prompt
77
tokens_completion
5698
native_tokens_prompt
81
native_tokens_completion
6029
native_tokens_completion_images
(null)
native_tokens_reasoning
5371
native_tokens_cached
16
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
0.00362739
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"e0a455f990b64a3092832eb987afdaa2"
is_byok
false
latency
367
model_permaslug
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
provider_name
"Mistral"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773829970-mBtzOVaqWTpPtjWSmsqV"
upstream_id
"e0a455f990b64a3092832eb987afdaa2"
total_cost
0.00362739
cache_discount
0.00000216
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
193
wordsDialogue
0
48.8138%