NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XFD35W6740D954EERZETX
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
18.2s
Cost:
$0.000114
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
70.52%
Dialogue to Total Word Ratio
(details)
35.2736%
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
"The target is the bouncy castle," Molly whispered. "Why the bouncy castle?" Bill asked. "Because that's where the gift pile is, Bill. It's a tactical stronghold of plushies and Legos." "I can't infiltrate a bouncy castle in a tuxedo, Molly." "Then wear a giant penguin suit. Blend in. Be the penguin." "A penguin? I have a reputation!" "Your reputation is 'man who once got stuck in a vending machine'. Now, do you have the distraction?" "I've got forty pounds of glitter and a bag of popping candy." "Perfect. You trigger the glitter-bomb near the cake, the children panic, the parents scramble, and I swoop in for the loot." "What about the security?" "The security is a golden retriever with a party hat. He's a pushover." "And the getaway?" "I've rented a motorized tricycle. We split the load." "A tricycle? I'm six-foot-four!" "Suck it up, Bill. Do you want the limited edition robotic dinosaurs or not?" "Fine. But I'm not wearing the beak." "You're wearing the beak, Bill. Be the penguin."
created_at
"2026-05-10T12:23:36.697Z"
5/10/2026, 12:23:36 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
722
moderation_latency
(null)
generation_time
10967
tokens_prompt
77
tokens_completion
278
native_tokens_prompt
79
native_tokens_completion
272
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
0.00011363
router
(null)
provider_responses
0
endpoint_id
"29b94af5-d8f8-419a-9cf1-ae1f2831142b"
is_byok
false
latency
96
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Venice"
status
429
1
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RbzwNberY7XvHzeRHrtJDN7F"
is_byok
false
latency
67
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-1778415816-Cl81O2GCLWVv1cixeO6K"
session_id
(null)
api_type
"completions"
id
"gen-1778415816-MI1kGDvcvGSNFsz3dWIu"
upstream_id
"chatcmpl-RbzwNberY7XvHzeRHrtJDN7F"
total_cost
0.00011363
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.03%
Matches word count
n/a
neededClean
false
words
170
70.52%
Dialogue to Total Word Ratio
Ratio: 97.69%, Deviation: 7.69%
neededClean
false
wordsTotal
173
wordsDialogue
169
35.2736%