NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY89SGPDAQ6K0W1H3W0MXGZ
Run Details
Model:
Ministral 3 14B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.2s
Cost:
$0.000033
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
75.66%
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 rain drummed against the old mansion’s grimy windows. Fog curled through the garden like a ghost’s slow breath. Detective Mara Voss adjusted her damp overcoat carefully. A single candle flickered in the abandoned study’s darkness. Footsteps echoed where no one should have walked recently. The air smelled of lavender and something far more sinister. A letter lay open on the desk, ink still wet. *"Meet me here—tonight,"* the words whispered a warning. Mara’s fingers brushed the page, feeling residue cold. Beyond the glass, a shadow moved too fast to see.
created_at
"2026-02-20T19:26:50.399Z"
2/20/2026, 7:26:50 PM
model
"mistralai/ministral-14b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
226
moderation_latency
(null)
generation_time
1055
tokens_prompt
46
tokens_completion
151
native_tokens_prompt
39
native_tokens_completion
127
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
0.0000332
router
(null)
provider_responses
0
endpoint_id
"0b53717b-9af5-4de3-80af-ebedd2adf981"
id
"6d802383527f4bd9aa9b17b5fe1f607c"
is_byok
false
latency
223
model_permaslug
"mistralai/ministral-14b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771615610-hv54ELTMp9OTrVNTpWRR"
upstream_id
"6d802383527f4bd9aa9b17b5fe1f607c"
total_cost
0.0000332
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
75.66%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
10
2
8
3
9
4
9
5
10
6
10
7
9
8
8
9
10