NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR9111PZ5BGGPZE5RK65BJBK
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 25s
Cost:
$0.002149
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
90.6364%
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
Molly spread the crayon-drawn blueprint across the dashboard of the rusted van. She pointed a manicured finger at the designated Cake Zone, her eyes gleaming with a predatory intensity usually reserved for museum heists. Bill stared at the drawing, blinking slowly while holding a bag of oversized clown shoes. He wondered why they were targeting a seven-year-old's birthday bash, but Molly’s conviction was terrifying. She detailed the infiltration strategy, which involved a tactical distraction using a smoke machine and a very loud recording of a crying baby. The target was the mahogany table in the den, currently piled high with shiny wrapping paper and expensive robotic dinosaur kits. Molly insisted that the security—a golden retriever named Buster—could be neutralized with a single strip of premium bacon. Bill sighed, adjusting his neon wig, feeling the absurdity of the mission settle in his bones. He looked at her. "Is the bacon organic?" he asked. Molly glared. "Just focus, Bill, the dinosaur kits are waiting!" she snapped. Bill frowned. "Do I really need this neon wig?" Molly ignored him. He sighed again, wondering if crime really paid this little.
created_at
"2026-05-10T13:25:33.544Z"
5/10/2026, 1:25:33 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
246
moderation_latency
(null)
generation_time
144953
tokens_prompt
77
tokens_completion
5063
native_tokens_prompt
82
native_tokens_completion
5626
native_tokens_completion_images
(null)
native_tokens_reasoning
4768
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
(null)
usage
0.00214854
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RWRaXKUpjlDW49iZa8CXujM7"
is_byok
false
latency
54
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778419533-L4oIqtsIdvETCgmFAWk4"
session_id
(null)
api_type
"completions"
id
"gen-1778419533-SsAXXRGxqWjS809u1rqC"
upstream_id
"chatcmpl-RWRaXKUpjlDW49iZa8CXujM7"
total_cost
0.00214854
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
191
wordsDialogue
19
90.6364%