NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ95B0GZ19VX5JHHM3NRBBEP
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.1s
Cost:
$0.007437
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
96.55%
Dialogue to Total Word Ratio
(details)
96.2665%
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
Messages
Meta
AI
"Put the nose on, Bill." "I look like a depressed radish," he muttered, tugging the elastic. "You look like a professional. The target is the gift table behind the bounce house." "The one with the slow leak?" "Precisely. When the sugar rush peaks and the screaming hits seventy decibels, we strike." "I hate the stickiness, Molly. Kids are just sentient jam magnets." "Focus. There are pristine Lego sets in there. The resale value is astronomical." "And the drone?" "Timmy’s getting a drone, but he won't be the one flying it. We bag the loot and exit via the plastic slide." "The curly one?" "The curly one." "My hips won't clear that radius, Molly." "Grease your jumpsuit. This is a high-stakes operation." "It’s a backyard in the suburbs." "It’s an unsecured vault filled with cardboard treasure. Do you have the distraction ready?" "I have three dozen half-inflated poodles," Bill said, gesturing to the bag. "Perfect. If any toddler asks for a sword, give them a giraffe. It confuses them." "If I get bitten, I’m leaving." "Just keep twisting balloons and nobody gets hurt." "Fine. But I’m keeping the nose. It hides my shame."
created_at
"2026-02-25T01:06:43.366Z"
2/25/2026, 1:06:43 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1710
moderation_latency
(null)
generation_time
15093
tokens_prompt
77
tokens_completion
1090
native_tokens_prompt
67
native_tokens_completion
2468
native_tokens_completion_images
0
native_tokens_reasoning
2168
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
0.0074375
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1708
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771981603-eFPV4YOzSrh4YowaL8iR"
upstream_id
(null)
total_cost
0.0074375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
96.55%
Dialogue to Total Word Ratio
Ratio: 94.33%, Deviation: 4.33%
neededClean
false
wordsTotal
194
wordsDialogue
183
96.2665%