NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8W05XZ00AME8MPJXTFP92K
Run Details
Model:
Gemini 3.1 Flash Lite (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.3s
Cost:
$0.000390
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3860%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The suburban cul-de-sac was currently infested with pint-sized agents of chaos, their sugary shrieks echoing against the brick facade of number forty-two. Molly adjusted her tactical balaclava, which was inexplicably patterned with cartoon daisies, and flattened herself against a manicured hedge. Beside her, Bill looked ridiculous in a neon vest, clutching a blueprint drawn entirely in glitter glue. He had acquired this intelligence from a seven-year-old informant known only as Timmy the Terror. The objective was clear: secure the mountain of wrapped boxes currently guarded by a clown with a suspicious stutter. They had practiced their extraction route through the bouncy castle maze for weeks. Molly checked her watch, the ticking sound muffled by the rhythmic thumping of pop music filtering through the open patio doors. The target perimeter remained vulnerable, though a stray golden retriever was currently sniffing Bill’s boots with investigative intensity. They had one shot before the cake ceremony triggered a security lockdown of sugar-fueled toddlers. Bill nudged her shoulder, his eyes wide behind his plastic mask. Ready to liberate the haul? Molly nodded, fingers tightening around her miniature crowbar. Let us secure the loot. They lunged forward, blending into the frantic whirlwind of children.
created_at
"2026-05-10T11:57:42.216Z"
5/10/2026, 11:57:42 AM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
482
moderation_latency
(null)
generation_time
2144
tokens_prompt
77
tokens_completion
331
native_tokens_prompt
67
native_tokens_completion
249
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
"standard"
usage
0.00039025
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"tnIAavDGGtfVz7IP1-eH-Ag"
is_byok
false
latency
482
model_permaslug
"google/gemini-3.1-flash-lite-20260507"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778414262-kSBvs4prstndYqbN4r97"
session_id
(null)
api_type
"completions"
id
"gen-1778414262-7v6zNFGhgxhzytiG0q7m"
upstream_id
"tnIAavDGGtfVz7IP1-eH-Ag"
total_cost
0.00039025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
205
wordsDialogue
0
68.3860%