NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRGYFPV22PFPPTDQQAHT6Y
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.1s
Cost:
$0.008863
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
77.08%
Dialogue to Total Word Ratio
(details)
88.4129%
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
"Did you secure the getaway vehicle?" Molly asked. "It is parked by the sandbox," Bill whispered. "A customized pedal kart with high-traction tires." "Are you insane? We need serious cargo capacity! We are hitting a spoiled seven-year-old’s birthday party, Bill. There are fifty wrapped boxes inside that heavily fortified bounce house." "The bounce house is impenetrable! Timmy’s uncle is guarding the perimeter dressed as a swashbuckling pirate." "Does he have a real parrot?" "No, but he has a plastic cutlass and looks dangerously caffeinated." "Stick to the plan. I crawl through the doggy door disguised as a giant plush dinosaur. You create the ultimate diversion." "What diversion?" "Throw three boxes of juice pouches into the ball pit and scream that the clown is giving away live ferrets. The toddlers will riot, the pirate will panic, and I will bag the high-end Lego sets." "What about the crown jewel? Little Timmy’s motorized mini-convertible?" "That is my extraction vehicle." "Do not forget the glitter bombs if things go south," Bill added. "Glitter is strictly a last resort. It never washes out of fleece." "Fair enough. But if they have chocolate cupcakes, the take is split fifty-fifty." "Deal. Put on your oversized party hat. It is showtime."
created_at
"2026-09-03T13:49:56.801Z"
9/3/2026, 1:49:56 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1743
moderation_latency
(null)
generation_time
7684
tokens_prompt
75
tokens_completion
1068
native_tokens_prompt
67
native_tokens_completion
2350
native_tokens_completion_images
0
native_tokens_reasoning
2050
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
0.00886275
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443396-ARCfqcl3MhQSN2uLp0bg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443396-cb9nD47DDjPCQLfhgbc6"
upstream_id
"BHuZaqjlOcbRjMcPp_eYwQ4"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"BHuZaqjlOcbRjMcPp_eYwQ4"
is_byok
false
latency
1733
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.00886275
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
99.74%
Matches word count
n/a
neededClean
false
words
204
77.08%
Dialogue to Total Word Ratio
Ratio: 97.14%, Deviation: 7.14%
neededClean
false
wordsTotal
210
wordsDialogue
204
88.4129%