Run: 2026-02-20-01KHY80QK8FX9BQ58X4BFT74W5

Run Details

Model:
Gemma 3 4B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.6s
Cost:
$0.000012
Provider:
DeepInfra

Evaluation summary

Score Evaluator
Details Link
76.67% 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

AI
Rain lashed against the windows, a mournful, dark display. Detective Harding arrived, stepping onto the slick, silent floor. The opulent study held an unsettling, chilling, vacant air. A single crimson stain bloomed upon the Persian rug’s side. Lord Ashworth lay motionless, a priceless antique beside him. His face was pale, reflecting a terrible, final doom. The housekeeper wept softly, clutching a delicate, white handkerchief. A priceless jewel box rested open, conspicuously empty now. Someone clearly intended this gruesome, violent act to happen. Harding began his investigation, examining every detail slowly now.
created_at"2026-02-20T19:21:53.522Z" 2/20/2026, 7:21:53 PM
model"google/gemma-3-4b-it"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency145
moderation_latency(null)
generation_time1450
tokens_prompt63
tokens_completion158
native_tokens_prompt46
native_tokens_completion127
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.000012
router(null)
provider_responses
0
endpoint_id"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id"chatcmpl-R7RP8p96gdvlHYACnAvoRAwD"
is_byokfalse
latency61
model_permaslug"google/gemma-3-4b-it"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771615313-rrKHatNaqIYRo6sIDHgU"
upstream_id"chatcmpl-R7RP8p96gdvlHYACnAvoRAwD"
total_cost0.000012
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
76.67% Matches word count n/a
neededCleanfalse
sentences10
wordCounts
09
19
29
310
49
59
69
79
89
99