NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HGH5VQHSRGS3K4M29Z52PN
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
16.9s
Cost:
$0.020803
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 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
Messages
Meta
AI
Molly adjusted her oversized foam nose quietly in the cracked rearview mirror of their rusty, nondescript surveillance van parked outside. "Are you positive that bouncing castle provides sufficient tactical cover against seven hyperactive children hopped on juice boxes?" Bill nervously chewed licorice while unrolling blueprints drawn in purple crayon across a cardboard box stacked with bright helium balloons. "Relax, partner. Thick commercial vinyl will easily hide our thermal signatures. We breach smoothly through the velcro emergency escape hatch near the giant slide." She aggressively jammed a crowbar into her baggy yellow pants, scattering plastic party favors and pastel confetti across dirty floorboards. "What about the mother? Karen possesses terrifying perimeter awareness and carries a loud megaphone capable of bursting our very fragile adult eardrums." Sweat dripped down his fake drawn whiskers as he inspected two oversized burlap sacks disguised as cheerful birthday gift bags. "I hired a polka band to play near the pinata. While everyone watches the donkey smash, we swiftly strike." "And every single Lego set belongs to us?" "Every drone, video game, and motorized scooter. Move out." Together, the two clumsy thieves pulled down their colorful knitted balaclavas and crept silently toward the unsuspecting festive backyard gate.
created_at
"2026-09-02T16:51:42.591Z"
9/2/2026, 4:51:42 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1907
moderation_latency
(null)
generation_time
16892
tokens_prompt
75
tokens_completion
1637
native_tokens_prompt
67
native_tokens_completion
5534
native_tokens_completion_images
0
native_tokens_reasoning
5280
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
0.02080275
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788367902-57YuzzZTqwLRItgV2wuL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788367902-QqU5UeOw48UeE4acmQ0q"
upstream_id
"HlSYapT9KLPSjMcPk_beoQ8"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"HlSYapT9KLPSjMcPk_beoQ8"
is_byok
false
latency
1907
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.02080275
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%