NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZRZBTQQRQV2XBN3C9EPY9
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
15.8s
Cost:
$0.000093
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
80.84%
Dialogue to Total Word Ratio
(details)
66.3811%
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 unfolded the blueprints of the suburban living room with the intensity of a general invading a small nation. She pointed a jagged fingernail toward the designated drop zone, which was currently occupied by a bouncy castle and three toddlers in dinosaur costumes. Bill leaned in, smelling faintly of old ham and desperation. He adjusted his oversized sunglasses, despite being indoors, and checked the tension on his grappling hook. The target was a mountain of brightly wrapped boxes piled precariously near the cake table. Molly meticulously calculated the trajectory of the confetti cannons to ensure their getaway path remained clear of glitter. She envisioned the chaos of a sugar-fueled riot as the perfect diversion for their tactical extraction of the Lego sets and remote-controlled cars. Bill tapped his chin, pondering the structural integrity of the gift table. He worried about the possibility of a sudden nap-time ceasefire. Molly glared at him, her eyes narrowing as she gripped a stopwatch. She believed the window of opportunity existed only during the chaotic singing of Happy Birthday. "Check the balloons," Molly whispered. "They are red," Bill replied.
created_at
"2026-05-10T13:03:40.418Z"
5/10/2026, 1:03:40 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
232
moderation_latency
(null)
generation_time
5546
tokens_prompt
77
tokens_completion
298
native_tokens_prompt
79
native_tokens_completion
219
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
0.00009349
router
(null)
provider_responses
0
endpoint_id
"69279254-6a96-4e9d-abc6-ea76e6bf8e97"
is_byok
false
latency
10077
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Novita"
status
504
1
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RwoIX9FaYdRDZThhincrQX0R"
is_byok
false
latency
46
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-1778418220-CPbQMaWXimrXYmqNmpY0"
session_id
(null)
api_type
"completions"
id
"gen-1778418220-TepVWGr92hgkzD2XURgD"
upstream_id
"chatcmpl-RwoIX9FaYdRDZThhincrQX0R"
total_cost
0.00009349
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
80.84%
Dialogue to Total Word Ratio
Ratio: 3.21%, Deviation: 6.79%
neededClean
false
wordsTotal
187
wordsDialogue
6
66.3811%