NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XMT1Q72MWNR7ARK4954FC
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 34s
Cost:
$0.002877
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9747%
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 dashboard of the getaway van, her finger tracing a path toward the patio. "We enter through the sliding door at exactly two," she commanded loudly. Bill scratched his chin, staring intently at a yellow smudge of mustard on the map. "What about the scary clown?" "Ignore the clown. Focus on the presents," she replied, pointing to a red circle. Bill looked skeptical, leaning back into the cracked, smelly vinyl seat. "Is there a chocolate cake?" "Yes, but we want LEGOs, not frosting," Molly snapped, adjusting her headset. "A cake distraction could definitely work," he suggested. Molly sighed, wondering why she had ever partnered with this man. "No distractions. We grab the bags before the piñata drops." "Is it a donkey piñata?" "Does it even matter?" "I hate donkeys," Bill whispered, glancing away. Molly groaned, feeling a massive migraine blooming behind her eyes. "It is a party, not a zoo. Wear the bear suit and be quiet." "Does the suit have deep pockets?" "No, that is why we have laundry bags," she clarified firmly. "I feel like we are overthinking this," Bill noted, checking his gold watch. "We are stealing from children. Be professional."
created_at
"2026-05-10T12:26:26.751Z"
5/10/2026, 12:26:26 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
321
moderation_latency
(null)
generation_time
213235
tokens_prompt
77
tokens_completion
6336
native_tokens_prompt
82
native_tokens_completion
7543
native_tokens_completion_images
(null)
native_tokens_reasoning
6033
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
0.002877
router
(null)
provider_responses
0
endpoint_id
"69279254-6a96-4e9d-abc6-ea76e6bf8e97"
is_byok
false
latency
381
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Novita"
status
429
1
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RQYrsM4apTW8frWqjEgKKbV5"
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-1778415986-KM5tbksJqEzzXspK02Qr"
session_id
(null)
api_type
"completions"
id
"gen-1778415986-VEWYA91BSjSHWTzCMilk"
upstream_id
"chatcmpl-RQYrsM4apTW8frWqjEgKKbV5"
total_cost
0.002877
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.95%
Dialogue to Total Word Ratio
Ratio: 51.50%, Deviation: 1.50%
neededClean
false
wordsTotal
200
wordsDialogue
103
99.9747%