NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-19-01M7SQ1JMR78PM622A7KQ4R3MF
Run Details
Model:
Gemini 4 Neon (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
39.1s
Cost:
$0.068151
Provider:
Google
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 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
Molly unrolled a crayon blueprint across the kitchen table. "The target is Timmy’s seventh birthday," Molly said. "High-end neighborhood," Bill whispered. "We talking Lego Star Wars?" "Better. A rumored PlayStation and three motorized mini-Jeeps." "Sweet mother of Fisher-Price. What’s security looking like?" "Brutal. Twelve sugar-crazed second graders patrolling the perimeter, two hovering PTA moms guarding the gift table, and a hired magician with suspiciously fast hands." "I hate magicians. They always know where the wallet is." "Focus, Bill. We infiltrate at fourteen hundred hours. That’s cake time." "Classic diversion. While they’re singing, I sweep the table?" "Negative. You’re the distraction. You’re going in as Bubbles the Clown." Bill groaned, crossing his arms. "Absolutely not. I have a reputation! I robbed the Louvre!" "You stole a baguette from the Louvre cafe, Bill. Put on the red nose." "Fine. How do we extract the loot?" "While you make balloon giraffes, I’ll rappel from the oak tree, snag the pile, and bounce." "Literally?" "Literally. The bouncy castle is underneath the drop zone. One big jump, right over the fence into the getaway minivan." "Wait. What if Timmy catches me?" "Give him a balloon sword and run." Bill sighed. "I better get the PlayStation."
created_at
"2026-11-19T10:53:37.823Z"
11/19/2026, 10:53:37 AM
model
"google/gemini-4-neon-20261118"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1588
moderation_latency
(null)
generation_time
39030
tokens_prompt
75
tokens_completion
1125
native_tokens_prompt
97
native_tokens_completion
4524
native_tokens_completion_images
0
native_tokens_reasoning
4199
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
0.068151
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1795085617-aW4PE71204jd9WH1tu8N"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1795085617-QLk0l4ADFLo85cYvCs0y"
upstream_id
"MdX-atvJNYew_9MP_fbnsAg"
provider_responses
0
endpoint_id
"cbc1d01f-e431-41ec-9abb-36c1a5b10cb4"
id
"MdX-atvJNYew_9MP_fbnsAg"
is_byok
false
latency
1588
model_permaslug
"google/gemini-4-neon-20261118"
provider_name
"Google"
status
200
total_cost
0.068151
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google"
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: 90.20%, Deviation: 0.20%
neededClean
false
wordsTotal
204
wordsDialogue
184
100.0000%