NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HK0WTRB7W8945VFMF5KN9G
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
21.6s
Cost:
$0.025329
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
Crouched behind a leafy hydrangea bush, Molly adjusted her binoculars, surveying the heavily fortified suburban backyard. A rainbow banner flapped menacingly near the sandbox. At two o'clock, the target showed peak vulnerability: pure, sugar fueled chaos. Twenty screaming children formed a noisy perimeter of sticky hands, wild greed, and spilled fruit punch. The ultimate prize sat completely unguarded upon the picnic table, an enormous mountain of glossy wrapping paper concealing remote control helicopters and pristine gaming consoles. Bill nervously patted his tactical pack, checking the juice boxes inside. Sweat dripped down his nose as his eyes darted toward the inflatable obstacle course. "The bouncy castle covers the blind spot," Molly whispered, pointing forward. "And the clown?" Bill asked, trembling. "Bribed with imported seltzer," she replied coolly. "Great. We bag the Lego sets." Bill gave a quick nod, pulling down his camouflage party hat. Molly tapped her golden stopwatch, inhaling the rich, buttery scent of warm chocolate fountain fumes. Operation Pinata was now officially live. If they moved fast, the duo could easily bypass the scary mother guarding the cupcakes, loot the entire ribboned gift table, and vault safely over the wooden fence before the musical chairs music stopped playing entirely.
created_at
"2026-09-02T17:35:14.803Z"
9/2/2026, 5:35:14 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2634
moderation_latency
(null)
generation_time
21422
tokens_prompt
75
tokens_completion
1818
native_tokens_prompt
67
native_tokens_completion
6741
native_tokens_completion_images
0
native_tokens_reasoning
6480
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
service_tier
"default"
usage
0.025329
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788370514-gVAo1BJogNOUO4Vj7tqh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788370514-WkIziu0XxMaj9yN0RGS8"
upstream_id
"U16YaogM3tCMxw_BxKagBg"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"U16YaogM3tCMxw_BxKagBg"
is_byok
false
latency
2634
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.025329
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
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%