NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91BH0W6NJTTVNSDGW8003A
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.2s
Cost:
$0.000116
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
25.9628%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 across the sticky kitchen table. "Listen, Bill, the target is the bounce house." Bill scratched his chin. "Why the bounce house?" "Because that is where the parents stash the loot to keep it away from the toddlers," she whispered. "What about the face paint?" Bill asked. "Crucial. We blend in as oversized clowns." Bill frowned. "I can't do a balloon animal, Molly." "Just pretend you're struggling with a poodle. It adds pathos," she snapped. "And the security?" Molly pointed to a photo of a golden retriever. "One dog. Easily bribed with a piece of premium ham." "I'm allergic to ham," Bill groaned. "Suck it up for the sake of the Lego sets," Molly commanded. "Fine. Do we have a getaway vehicle?" "A motorized tricycle I stole from a brat in Jersey. It's stealthy." Bill stared at her. "We are going to get arrested by a seven-year-old." "Not if we hit the cake table first," Molly grinned. "Sugar rush, then we vanish." "I want the giant teddy bear," Bill insisted. "Focus, Bill! The operation begins at the first bubble machine blast."
created_at
"2026-05-10T13:31:16.9Z"
5/10/2026, 1:31:16 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
252
moderation_latency
(null)
generation_time
8060
tokens_prompt
77
tokens_completion
296
native_tokens_prompt
79
native_tokens_completion
278
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
0.00011591
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RH80aqM2zURQABvqJw29YGDe"
is_byok
false
latency
86
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-1778419876-yHQBhV2urU3A3cSR6XyY"
session_id
(null)
api_type
"completions"
id
"gen-1778419876-Bf142rtxrrvGyi7ollv2"
upstream_id
"chatcmpl-RH80aqM2zURQABvqJw29YGDe"
total_cost
0.00011591
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
0.00%
Dialogue to Total Word Ratio
Ratio: 77.42%, Deviation: 27.42%
neededClean
false
wordsTotal
186
wordsDialogue
144
25.9628%