NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7PCZB3CZCCA65Z4BVQKVF
Run Details
Model:
Gemma 3 4B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.5s
Cost:
$0.000011
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
63.48%
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
Rain hammered relentlessly against the ancient, darkened mansion walls. Inside, a chilling silence hung heavy in the air. Detective Harding arrived, searching for a missing, wealthy man. The local police found a scene quite disturbing indeed. Crimson stains spread across the Persian rug below. A shattered vase lay amidst the scattered, broken glass. Someone deliberately murdered him, a truly awful crime. Harding examined the victim, his expression grim and cold. He noted a single playing card clutched in his hand. This perplexing puzzle demanded immediate, careful investigation now.
created_at
"2026-02-20T19:16:14.963Z"
2/20/2026, 7:16:14 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
197
moderation_latency
(null)
generation_time
1398
tokens_prompt
63
tokens_completion
149
native_tokens_prompt
46
native_tokens_completion
114
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
0.00001096
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RLQrYfEXDwfiSNBD04lBlyhf"
is_byok
false
latency
57
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771614974-9ZP8f9orGObh9pj035K2"
upstream_id
"chatcmpl-RLQrYfEXDwfiSNBD04lBlyhf"
total_cost
0.00001096
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
63.48%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
9
2
9
3
9
4
8
5
9
6
8
7
9
8
10
9
8