Run: 2026-02-20-01KHYA5BCR5A5ZFNMFABW80FJC

Run Details

Model:
Gemma 3 4B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.2s
Cost:
$0.000011
Provider:
DeepInfra

Evaluation summary

Score Evaluator
Details Link
88.48% 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

AI
Rain lashed against the windows, a gloomy, somber sight. Detective Harding surveyed the room with a critical, watchful eye. The victim lay motionless, a crimson stain upon the rug. A priceless antique clock stood silent, stopped at precisely ten. Guests whispered nervously, displaying obvious shock and deep dismay. The butler claimed ignorance, a practiced, unsettling facade shown. A single, muddy footprint marred the polished wooden floor now. Someone had clearly entered, intent on causing this dark deed. Harding began his investigation, meticulously searching for any clue.
created_at"2026-02-20T19:59:22.019Z" 2/20/2026, 7:59:22 PM
model"google/gemma-3-4b-it"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency129
moderation_latency(null)
generation_time1101
tokens_prompt63
tokens_completion147
native_tokens_prompt46
native_tokens_completion113
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"
usage0.00001088
router(null)
provider_responses
0
endpoint_id"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id"chatcmpl-RlpzqGRZ1rreQAmXMQKWtTfH"
is_byokfalse
latency50
model_permaslug"google/gemma-3-4b-it"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771617562-PaCBQASJBqxRQ8pR0PZA"
upstream_id"chatcmpl-RlpzqGRZ1rreQAmXMQKWtTfH"
total_cost0.00001088
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
88.48% Matches word count n/a
neededCleanfalse
sentences9
wordCounts
09
110
210
310
49
59
610
710
89