Run: 2026-02-20-01KHY7YJS5BKMBYPKYFD4JZ53C

Run Details

Model:
Gemma 3 12B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
4.8s
Cost:
$0.000018
Provider:
DeepInfra

Evaluation summary

Score Evaluator
Details Link
87.04% 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, dark and quite severe. A chilling wind howled through ancient trees, causing dreadful fear. Lord Ashworth lay sprawled upon the Persian rug, lifeless now. His monocle rested askew, reflecting the room's gloomy glow. The opulent study felt strangely silent, holding secrets deep. Inspector Davies arrived promptly, surveying the scene with care. A single crimson rose lay near his still, pale hand. Lady Ashworth wept uncontrollably, clutching a delicate lace fan. The butler stood rigid, awaiting Davies’ first stern command. Something felt terribly wrong here, a darkness hard to see.
created_at"2026-02-20T19:20:43.063Z" 2/20/2026, 7:20:43 PM
model"google/gemma-3-12b-it"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency446
moderation_latency(null)
generation_time4683
tokens_prompt63
tokens_completion157
native_tokens_prompt46
native_tokens_completion126
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"
usage0.00001822
router(null)
provider_responses
0
endpoint_id"eb06dc92-5a16-47ec-a776-6ef956457c47"
id"chatcmpl-RCPWsvvcyP5PubhGO1sk88vu"
is_byokfalse
latency57
model_permaslug"google/gemma-3-12b-it"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771615243-WefXSzvPEv9Dp4C4nzz0"
upstream_id"chatcmpl-RCPWsvvcyP5PubhGO1sk88vu"
total_cost0.00001822
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
87.04% Matches word count n/a
neededCleanfalse
sentences10
wordCounts
010
110
210
39
49
59
610
79
89
910