NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR905WS5BA3ZSSX90H94HEG2
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
12.3s
Cost:
$0.000096
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The scent of cinnamon and burnt sugar hung heavy in the air, mingling with the floral notes of a fresh bouquet of lilies on the counter. Outside, the cobblestone streets of Oakhaven were slick with a sudden autumn drizzle. "He wasn't the type to just vanish, was he?" "Not since the town council meeting. He was practically vibrating with indignation over the zoning laws." "And you’re sure the door was locked from the inside?" "Bolted shut. I had to use the spare key from the flour bin just to get in here this morning." A silver tong clicked against a metal tray of lemon tarts, the sound sharp in the quiet shop. "The police are calling it a tragic accident, but look at the sugar dusting on the floor. Those aren't footprints." "They look more like drag marks." "Exactly. Now, do you want a raspberry scone, or are we going to keep pretending we aren't investigating a crime scene before the coffee has even brewed?" "Scone. Definitely the scone."
created_at
"2026-05-10T13:10:43.76Z"
5/10/2026, 1:10:43 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
102
moderation_latency
(null)
generation_time
12175
tokens_prompt
81
tokens_completion
255
native_tokens_prompt
80
native_tokens_completion
226
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
0.00009628
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-R9uM7kzgOfAam12csPcI9Ogv"
is_byok
false
latency
55
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-1778418643-BvWGS5Z11iVrhsJBYM5s"
session_id
(null)
api_type
"completions"
id
"gen-1778418643-e5L2e6JUmqb8CmMAl7Pn"
upstream_id
"chatcmpl-R9uM7kzgOfAam12csPcI9Ogv"
total_cost
0.00009628
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)