NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTHXXZKNN179SEVE3XVQ31
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.5s
Cost:
$0.029808
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
86.94%
Dialogue to Total Word Ratio
(details)
93.4615%
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
"Target is Timmy, age five," Molly whispered, pointing at the blueprint. "High-value loot is stacked behind the bounce house." "Are we talking high-end Lego sets or duplicate board games?" Bill asked. "Pure Lego gold, Bill. But security is tight. The juice box patrol hits at twelve, followed by fifty sugar-crazed toddlers." "What about the threat in the big red nose?" "Barnaby the Clown. Completely unpredictable. He twists a mean balloon animal." "Do we have a distraction?" "I hired Captain Sparkles, a discount magician. He will draw the parents away with terrible card tricks." "Brilliant. Once the piƱata ruptures, total chaos reigns. That is our window to nab the wrapped boxes." "We pack them into fake diaper bags and exit through the doggy door." "Did you bring the wire cutters?" "For what?" "To cut through the decorative ribbon on the giant teddy bear, obviously." "Good thinking. What if the birthday boy spots us?" "Drop a handful of sugar-free gummy bears and make a break for the getaway minivan." "What if the bouncy castle loses pressure?" "We pivot to the sandbox route." "You are a criminal mastermind, Molly." "I know. Now put on your glittery party hat, Bill, and let us go get rich."
created_at
"2026-07-25T14:23:35.368Z"
7/25/2026, 2:23:35 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1449
moderation_latency
(null)
generation_time
16485
tokens_prompt
75
tokens_completion
1615
native_tokens_prompt
67
native_tokens_completion
3961
native_tokens_completion_images
0
native_tokens_reasoning
3664
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
0.029808
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"58Zkavj2Guu4sOIPi6i1yQw"
is_byok
false
latency
1449
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-1784989415-Wl0bL9p2ZnaFAukwaJgJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989415-LFWkfTwovJzOPXosT3dh"
upstream_id
"58Zkavj2Guu4sOIPi6i1yQw"
total_cost
0.029808
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
99.98%
Matches word count
n/a
neededClean
false
words
202
86.94%
Dialogue to Total Word Ratio
Ratio: 96.12%, Deviation: 6.12%
neededClean
false
wordsTotal
206
wordsDialogue
198
93.4615%