NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHVP33YV3CBV1KCGK2QYY2EC
Run Details
Model:
Gemini 3.1 Pro (Preview)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 3s
Cost:
$0.088790
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Messages
Meta
AI
Molly adjusted her tactical binoculars, scanning the chaotic backyard of a suburban mansion. The objective was a towering pile of brightly wrapped packages arranged dangerously close to a dinosaur bouncy castle. This was the most prestigious birthday bash of the season, a veritable goldmine of unearned wealth targeted at a rather spoiled little child named Timmy. Bill sat beside her in the getaway minivan, nervously checking the velcro straps on his stealth sneakers. He had spent three grueling hours studying the blueprints of the patio, memorizing the blind spots between the chocolate fountain and the petting zoo. They were dressed in black turtlenecks, entirely inappropriate for a sweltering July afternoon, but absolute professionalism was always required for a major job. "The creepy clown is our entry window." Molly lowered her lenses, wiping a bead of sweat from her forehead. She pulled a detailed map from her pocket, tracing a route past the snoozing grandparents. "We strike during the balloon animals." Bill carefully checked his oversized dark duffel bag to ensure they brought enough decoy juice boxes to throw off potential pursuit. "Grab the big Lego sets first, okay?" Molly eventually flashed a very devious grin of complete approval toward him.
created_at
"2026-02-19T19:30:08.316Z"
2/19/2026, 7:30:08 PM
model
"google/gemini-3.1-pro-preview-20260219"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3833
moderation_latency
(null)
generation_time
62664
tokens_prompt
77
tokens_completion
2373
native_tokens_prompt
67
native_tokens_completion
7388
native_tokens_completion_images
0
native_tokens_reasoning
7141
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.08879
router
(null)
provider_responses
0
endpoint_id
"2abf5677-0826-45d9-8470-3d62c31d54a1"
is_byok
false
latency
3833
model_permaslug
"google/gemini-3.1-pro-preview-20260219"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771529408-7IOyx4sZ4pYWBV4xGt59"
upstream_id
(null)
total_cost
0.08879
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%