Run: 2026-03-11-01KKFMEB43BMDR3G873028JPAJ

Run Details

Duration:
10.1s
Cost:
$0.000000
Provider:
Stealth

Evaluation summary

Score Evaluator
Details Link
0.00% Matches word count (details)
96.56% Dialogue to Total Word Ratio (details)
48.2788% 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
Molly peered through binoculars at the suburban house. “Target acquired. Cake’s on the table. Balloons are— Bill, are those clown shoes?” “Disguise, Molls. We blend in.” “You look like a giant, terrified duck. The plan?” “Simple. You cause a diversion. I slip in, grab the loot, slip out.” “What kind of diversion?” “Classic. Piñata. You swing, miss spectacularly, kids scatter for candy. I move.” “I’m not hitting a piñata, Bill. That’s kids’ stuff.” “You’re literally stealing their presents. Your moral line is a piñata?” “Fine. But I’m using the comically large hammer.” “Of course. Now, the getaway vehicle—” “Don’t say the unicycle.” “It’s silent! And fits in the alley!” “It’s one wheel! We have sacks of toys!” “Details, details. On my signal, you swing.” “This is the dumbest heist we’ve ever planned.” “Dumber than the petting zoo?” “…Marginally. Okay, I’m swinging.”
created_at"2026-03-11T23:41:49.583Z" 3/11/2026, 11:41:49 PM
model"openrouter/hunter-alpha"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1680
moderation_latency(null)
generation_time10046
tokens_prompt77
tokens_completion520
native_tokens_prompt2111
native_tokens_completion430
native_tokens_completion_images(null)
native_tokens_reasoning234
native_tokens_cached1984
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
router(null)
provider_responses(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773272509-fwx6kXMs3GP4L7pziabP"
upstream_id"gen-1773272509-fwx6kXMs3GP4L7pziabP"
total_cost0
cache_discount(null)
upstream_inference_cost0
provider_name"Stealth"

Evaluation details

Result Evaluator Details Meta Data
0.00% Matches word count n/a
neededCleanfalse
words141
96.56% Dialogue to Total Word Ratio
Ratio: 94.33%, Deviation: 4.33%
neededCleanfalse
wordsTotal141
wordsDialogue133
48.2788%