NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8Y86P8HPYAG4M1YCZGTAX6
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16m 11s
Cost:
$0.004510
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 blueprints of the suburban living room across the greasy dashboard of the getaway van. She pointed a manicured finger at the strategic placement of the bounce house, which served as the primary perimeter obstacle. Bill chewed on a toothpick, staring intently at the guest list. He was concerned about the tactical deployment of the toddlers, whose chaotic movements were notoriously unpredictable. The primary targets were the piles of brightly wrapped boxes clustered precariously near the chocolate cake. Molly had calculated the exact window of opportunity to occur the moment the piƱata burst and maximum distraction ensued. Bill adjusted his fake mustache, feeling the adhesive slip in the oppressive humidity. He wondered if a full clown costume would provide better camouflage among the party guests. Molly sighed, reminding him that stealth was paramount for a job of this magnitude. They had a precise three-minute window before the sugar crash hit the children and the exhausted parents regained their vigilance. Bill checked his gold watch, nodded solemnly, and tightened his grip on the burlap sack. "Are we ready for the mayhem, Bill?" Molly whispered. "I hope there are LEGOs," Bill replied. "And maybe some of those really fancy puzzles."
created_at
"2026-05-10T12:37:02.288Z"
5/10/2026, 12:37:02 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
843
moderation_latency
(null)
generation_time
971066
tokens_prompt
77
tokens_completion
9060
native_tokens_prompt
81
native_tokens_completion
11246
native_tokens_completion_images
(null)
native_tokens_reasoning
8739
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
0.00450974
router
(null)
provider_responses
0
endpoint_id
"69279254-6a96-4e9d-abc6-ea76e6bf8e97"
id
"6851354a7ab6ba01e579568870145512"
is_byok
false
latency
585
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778416622-4WcHhSPgsQCa859OgzmH"
session_id
(null)
api_type
"completions"
id
"gen-1778416622-Y9RWlf54gusFo01trsq7"
upstream_id
"6851354a7ab6ba01e579568870145512"
total_cost
0.00450974
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%