NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB5J3K2FWZ5PMGFKD74TQQ
Run Details
Model:
Gemma 3 4B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.8s
Cost:
$0.000011
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
65.29%
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. Detective Harding surveyed the scene, grim and quite alone. A wealthy patriarch lay lifeless, shockingly cold and still. Crimson stained the plush rug, a terrible, awful sight. The butler stood frozen, his expression utterly distraught now. A single gunshot echoed, confirming brutal, violent demise here. Investigators questioned the staff, each voice nervous and slow. The victim’s prized collection seemed completely undisturbed, strangely. Something felt deliberately staged, a calculated, cruel deceit. Harding knew this case held secrets, deeply hidden indeed.
created_at
"2026-02-20T20:16:57.47Z"
2/20/2026, 8:16:57 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
182
moderation_latency
(null)
generation_time
1626
tokens_prompt
63
tokens_completion
162
native_tokens_prompt
46
native_tokens_completion
120
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
0.00001144
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RbqBIpXKk7u2vfz1vKbfoKSj"
is_byok
false
latency
76
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618617-R4Dn7IBr4FiiAdoeGBPh"
upstream_id
"chatcmpl-RbqBIpXKk7u2vfz1vKbfoKSj"
total_cost
0.00001144
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
65.29%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
9
2
9
3
9
4
9
5
9
6
9
7
8
8
8
9
9