Run: 2026-02-20-01KHYADWQK6HWJYA6B4S8XWCGT

Run Details

Duration:
7.2s
Cost:
$0.000046
Provider:
DeepInfra

Evaluation summary

Score Evaluator
Details Link
0.00% Matches word count (details)
99.91% Dialogue to Total Word Ratio (details)
49.9558% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.

Model response

AI
“Right, so inflatable castle, confirmed?” Molly asked, sketching furiously in a notebook. “Confirmed. Three-year-old terror zone, apparently. Distraction central,” Bill replied, polishing his glasses with a slightly grubby handkerchief. “Excellent. And the parents?” “Totally engrossed in polite conversation about organic quinoa and screen time. Blind as bats.” “Good, good. Now, the presents. Intelligence suggests a significant haul. LEGO, apparently.” “LEGO? Molly, are you serious? We’re risking jail time for plastic bricks?” “High-value plastic bricks, Bill! Think resale! Think early retirement!” “Retirement? We’re barely out of our twenties!” “Details, details. Okay, you create a diversion. Maybe ‘accidentally’ release all the party balloons?” “Classic. But effective. What about you?” “I’m going for the gift bags. Swift, silent, surgical. Present acquisition commencing in five…” “Wait, five what? Minutes? Molly, you didn’t tell me the timing!” “Of course I did! It’s written right here! …Oh. Never mind.”
created_at"2026-02-20T20:04:01.916Z" 2/20/2026, 8:04:01 PM
model"google/gemma-3-27b-it"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency468
moderation_latency(null)
generation_time6989
tokens_prompt93
tokens_completion307
native_tokens_prompt75
native_tokens_completion250
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"
usage0.000046
router(null)
provider_responses
0
endpoint_id"8f22002c-c045-446f-a1b9-9896133536b8"
id"chatcmpl-RUAnVTJMBCVY3TJIwQxDzwWo"
is_byokfalse
latency67
model_permaslug"google/gemma-3-27b-it"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771617841-rq60J81EdoG7UYOZt4GR"
upstream_id"chatcmpl-RUAnVTJMBCVY3TJIwQxDzwWo"
total_cost0.000046
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
0.00% Matches word count n/a
neededCleanfalse
words145
99.91% Dialogue to Total Word Ratio
Ratio: 88.28%, Deviation: 1.72%
neededCleanfalse
wordsTotal145
wordsDialogue128
49.9558%