NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTWVBXDDXKWP65E5Z2ZN1T
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.8s
Cost:
$0.002253
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
0.5229%
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
"You brought a bouncy castle?" Molly hissed, crouching behind the hibiscus bushes. "It’s an infiltration device," Bill whispered back, adjusting his oversized rainbow wig. "We climb inside, bounce over the perimeter fence, and snag the target." "The target is a stack of Paw Patrol boxes, Bill. They're on the patio!" "Precisely. High-value loot." Bill checked his watch. "The sugar crash hits in two minutes. The small humans will be incapacitated by juice boxes and cake." "And the parents?" "Distracted by a clown." Molly squinted. "Where’s the clown?" "You're looking at him." Bill pulled a red nose from his pocket and slapped it onto his face. "Pretty clever, right?" "You look like a nightmare," Molly said, peeking through the leaves. "Wait. Is that kid eating grass?" "Focus, Molly! What's the entry protocol?" "We walk in, grab the LEGO, walk out." "And the distraction?" "I’ll pretend I lost my imaginary puppy." "Brilliant," Bill chuckled, untying the bouncy castle strap. "They'll be weeping. Now, on my mark, we bounce." "I am not bouncing, Bill." "Ready?" "No." "Go!"
created_at
"2026-07-25T14:29:33.188Z"
7/25/2026, 2:29:33 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
528
moderation_latency
(null)
generation_time
2689
tokens_prompt
75
tokens_completion
286
native_tokens_prompt
67
native_tokens_completion
287
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.002253
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"TchkaoGDEpDTjMcPnuef6AY"
is_byok
false
latency
528
model_permaslug
"google/gemini-3.6-flash-20260721"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784989773-EQwmbKiXAFbNGRDAmqaO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989773-RD4usU7v7BsdrSaV3zDA"
upstream_id
"TchkaoGDEpDTjMcPnuef6AY"
total_cost
0.002253
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
174
0.01%
Dialogue to Total Word Ratio
Ratio: 72.57%, Deviation: 17.43%
neededClean
false
wordsTotal
175
wordsDialogue
127
0.5229%