NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAB1BJZWC4N983W23C17KX
Run Details
Model:
Ministral 3 8B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.2s
Cost:
$0.000027
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
78.25%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The old manor loomed darkly under stormy midnight skies. Rain lashed windows as thunder shook the crumbling stone walls. A lone figure stumbled through the overgrown, twisted garden path. Footsteps echoed hollowly on the cracked, rain-slicked flagstones below. The front door creaked open with a slow, sinister groan. Inside, flickering candlelight revealed a body sprawled motionless. Blood pooled darkly beneath the victim’s lifeless, outstretched hand. A single playing card lay face-up near the corpse’s cold fingers. The detective arrived just as the first police officers rushed inside. Whispers of betrayal and secrets filled the chilling, damp air.
created_at
"2026-02-20T20:02:28.352Z"
2/20/2026, 8:02:28 PM
model
"mistralai/ministral-8b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
194
moderation_latency
(null)
generation_time
1086
tokens_prompt
46
tokens_completion
173
native_tokens_prompt
39
native_tokens_completion
143
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
0.0000273
router
(null)
provider_responses
0
endpoint_id
"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id
"161ad719cd004d21a11035b742613f0a"
is_byok
false
latency
194
model_permaslug
"mistralai/ministral-8b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771617748-tUTSZXvEjDfqYvCpDL6T"
upstream_id
"161ad719cd004d21a11035b742613f0a"
total_cost
0.0000273
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
78.25%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
10
2
10
3
10
4
10
5
8
6
9
7
12
8
11
9
10