NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07CK1Y3J8EEG3MSESAHRH7
Run Details
Model:
Mistral Small 4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
35.9s
Cost:
$0.003538
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
96.68%
Dialogue to Total Word Ratio
(details)
98.3333%
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
By the daycare’s flickering light, plans took shape. Bill: "You’ve got chocolate on your Al Capone hat." Molly: "So do you. Also, why are we wearing disguises for stealing Play-Doh?" Bill: "Because if we’re caught, I’m not going to jail as Bill. I’ll be ‘Action Jackson’ from now on." Molly: "Noted. So, presents are by the clown balloon arch?" Bill: "No, they’re in the ‘Prize Vault’—a kiddie pool filled with stuffed animals." Molly: "A pool? Who thought that was safe?" Bill: "Some parent’s Pinterest fail. Our advantage." Molly: "Timing’s everything. Cake time?" Bill: "7:30. We hit at 7:35 when adults are weak from sugar." Molly: "And kids are hyper from sugar?" Bill: "Exactly. Chaos is our middle name." Molly: "Or ‘disaster.’" Bill: "Same letters, same crime." Bill: "Backup plan if the kiddie pool’s a trap?" Molly: "There is none. We improvise or we improvise poorly." Bill: "Not reassuring." Molly: "Then picture your future self on a stolen tricycle, laughing maniacally." Bill: "Now I’m in. Let’s go get those presents before someone invites us to the piñata." Molly: "Deal. First one to grab a My Little Pony gets bragging rights." Bill: "I call all of them." Molly: "Greedy. That’s why you’re my partner."
created_at
"2026-03-18T10:20:46.026Z"
3/18/2026, 10:20:46 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
362
moderation_latency
(null)
generation_time
35716
tokens_prompt
77
tokens_completion
5099
native_tokens_prompt
81
native_tokens_completion
5877
native_tokens_completion_images
(null)
native_tokens_reasoning
4761
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
0.00353835
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"76ab4874b4f542f38b03f3d52a522a62"
is_byok
false
latency
357
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-1773829246-kVux8ETwStSt7YUUoR8F"
upstream_id
"76ab4874b4f542f38b03f3d52a522a62"
total_cost
0.00353835
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
96.68%
Dialogue to Total Word Ratio
Ratio: 85.71%, Deviation: 4.29%
neededClean
false
wordsTotal
203
wordsDialogue
174
98.3333%