NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8VEW74MD2XJWJDM6WG6WT4
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
27.5s
Cost:
$0.000133
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
0.08%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.4364%
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
"Are we really doing this, Bill?" "Yes, Molly. Now hold the map." "It’s a hand-drawn crayon sketch of a backyard." "It’s tactical. See the X? That’s the gift pile." "We’re robbing a six-year-old's birthday party." "Strategically acquiring surplus toys, Molly. Get it right." "What’s the plan for the perimeter?" "I’ll distract the parents with a fake allergy scare. You swoop in, bag the LEGO sets, and vanish." "And the children?" "They’re chaotic. We blend in." "Blend in? I'm thirty-four!" "Wear a party hat. Put on a tutu. Just look whimsical." "I am not wearing a tutu to commit a felony." "It's a misdemeanor at best. Now, do you have the distraction device?" "The bubble machine?" "Exactly. Bubbles create visual interference. It's basic stealth." "You’ve watched too many movies." "And you're thinking too much. Now, put on the tutu." "I hate you." "You love the thrill. Now, let's go. On my mark, we deploy the bubbles." "Fine. But if I get glitter on my boots, I'm stealing your car." "Deal. Ready? Go!"
created_at
"2026-05-10T11:48:15.399Z"
5/10/2026, 11:48:15 AM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2534
moderation_latency
(null)
generation_time
27059
tokens_prompt
77
tokens_completion
296
native_tokens_prompt
79
native_tokens_completion
305
native_tokens_completion_images
(null)
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
(null)
usage
0.00013306
router
(null)
provider_responses
0
endpoint_id
"29b94af5-d8f8-419a-9cf1-ae1f2831142b"
is_byok
false
latency
109
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Venice"
status
429
1
endpoint_id
"69279254-6a96-4e9d-abc6-ea76e6bf8e97"
id
"6871fca445d9bf55b91c9c15719b4599"
is_byok
false
latency
2382
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-1778413695-YIOCySaPxnJW3mDmcr7y"
session_id
(null)
api_type
"completions"
id
"gen-1778413695-B3VryL81KAAiOSFD6d59"
upstream_id
"6871fca445d9bf55b91c9c15719b4599"
total_cost
0.00013306
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.08%
Matches word count
n/a
neededClean
false
words
171
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
175
wordsDialogue
175
18.4364%