NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYA3NQ124X3ZXPBGDXGF74Y
Run Details
Model:
Ministral 3 3B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.9s
Cost:
$0.000015
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
52.60%
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 grand ballroom glows with candlelight softly. Velvet drapes sway gently as guests gather tonight. A mysterious note lies hidden beneath the piano’s keys. Whispers fill the air, though no one speaks aloud. Elegant dresses shimmer under the flickering gaslight. A single shadow lingers near the grand staircase’s edge. The clock strikes midnight, marking the final hour. Something feels amiss beneath the polished marble floor. A hand clutching a silver flask trembles near the door. The guests turn toward the sound of a distant scream.
created_at
"2026-02-20T19:58:27.053Z"
2/20/2026, 7:58:27 PM
model
"mistralai/ministral-3b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1036
moderation_latency
(null)
generation_time
1781
tokens_prompt
46
tokens_completion
143
native_tokens_prompt
39
native_tokens_completion
115
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
0.0000154
router
(null)
provider_responses
0
endpoint_id
"b9f6828f-aef9-498a-91f5-6816fbf72420"
id
"d3ee9c760b9c4715a00e71b33dec5ade"
is_byok
false
latency
981
model_permaslug
"mistralai/ministral-3b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771617507-1tabu9asmQ9NuPT9tlcd"
upstream_id
"d3ee9c760b9c4715a00e71b33dec5ade"
total_cost
0.0000154
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
52.60%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
7
1
8
2
9
3
9
4
7
5
9
6
8
7
8
8
10
9
10