Run: 2026-02-25-01KJ94TS6TX2ARPAG6WJ9WFZP1

Run Details

Duration:
41.8s
Cost:
$0.025437
Provider:
Google AI Studio

Evaluation summary

Score Evaluator
Details Link
99.74% Matches word count (details)
100.00% Dialogue to Total Word Ratio (details)
99.8718% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 adjusted her binoculars, staring at the suburban fortress where balloons bobbed like colorful air-mines. Bill checked his pockets nervously, rattling a plastic whistle. Molly sighed, tapping the steering wheel. They sat in the cramped van, the air smelling of stale fries and wet dog. The heist of the century—or at least the third grade—was beginning. Outside, a swarm of toddlers shrieked while a bouncy castle rattled in the wind. Bill gripped a stolen Frozen tablecloth. Molly gripped her hand-drawn map of the backyard playground. She looked at his trembling hands and frowned before finally speaking. "The bounce house is the diversion." "I only have glitter glue and a juice box." "Stay focused. We need those Legos. The target is the gift table." "The clown looks stabby, Molly." "He's a professional. Like us. Do you have the camouflage?" "I have a Frozen tablecloth." "Perfect. Once the cake arrives, the sugar rush creates pure chaos." "What if I get a goody bag?" "Take it. Just don't get distracted by bubbles." "Keep your eyes on the Star Wars sets." "Shut up. Put on your mask." "Batman or the bunny?" "Bunny. It's a birthday, not a funeral."
created_at"2026-02-25T00:57:51.589Z" 2/25/2026, 12:57:51 AM
model"google/gemini-3-flash-preview-20251217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1759
moderation_latency(null)
generation_time41711
tokens_prompt77
tokens_completion2684
native_tokens_prompt67
native_tokens_completion8468
native_tokens_completion_images0
native_tokens_reasoning8188
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"
usage0.0254375
router(null)
provider_responses
0
endpoint_id"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byokfalse
latency1759
model_permaslug"google/gemini-3-flash-preview-20251217"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771981071-26u73yHJeJkbdjYcTpCF"
upstream_id(null)
total_cost0.0254375
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"

Evaluation details

Result Evaluator Details Meta Data
99.74% Matches word count n/a
neededCleanfalse
words196
100.00% Dialogue to Total Word Ratio
Ratio: 49.49%, Deviation: 0.51%
neededCleanfalse
wordsTotal198
wordsDialogue98
99.8718%