Run: 2026-02-20-01KHYAEYK85Q334QWQNSHPY3K0

Run Details

Model:
Gemma 3 12B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
7.1s
Cost:
$0.000019
Provider:
DeepInfra

Evaluation summary

Score Evaluator
Details Link
84.45% 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 manor windows, a furious, chilling grey storm. Lord Ashworth lay lifeless within his study, a grim, silent tableau. Inspector Davies surveyed the opulent room, observing every shadowed corner. A single crimson stain bloomed upon the Persian rug's intricate design. Servants whispered nervously, huddled together, fearing dreadful consequences now. The air possessed a heavy scent of lilies and bitter almonds. Lady Ashworth wept dramatically, clutching a delicate, embroidered handkerchief. Young Master Thomas glared suspiciously, maintaining a carefully cultivated aloofness. A priceless antique clock ticked slowly, marking passing, dreadful minutes. Something felt terribly wrong within this grand, historic, stately home.
created_at"2026-02-20T20:04:36.597Z" 2/20/2026, 8:04:36 PM
model"google/gemma-3-12b-it"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency503
moderation_latency(null)
generation_time6781
tokens_prompt63
tokens_completion188
native_tokens_prompt46
native_tokens_completion134
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"
usage0.00001926
router(null)
provider_responses
0
endpoint_id"eb06dc92-5a16-47ec-a776-6ef956457c47"
id"chatcmpl-RdSnP1Ih2uABVgMnHGC8wHvE"
is_byokfalse
latency51
model_permaslug"google/gemma-3-12b-it"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771617876-3iCUOjJ2loGamASZ44au"
upstream_id"chatcmpl-RdSnP1Ih2uABVgMnHGC8wHvE"
total_cost0.00001926
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
84.45% Matches word count n/a
neededCleanfalse
sentences10
wordCounts
011
111
210
311
49
511
69
710
810
910