NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YKJWVN7PGRQ2CWJ83NTJH
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.9s
Cost:
$0.000107
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 clung to the floral wallpaper of The Golden Crust. Outside, a drizzle blurred the cobblestones of Main Street, but inside, the air was warm and thick with the promise of lemon tarts. "You can’t possibly think he did it." "The man has a motive as clear as a summer morning, Clara. And he was seen leaving the library ten minutes before the alarm went off." "Being in the vicinity isn't a crime. Besides, Arthur is far too clumsy to steal a first edition without knocking over every bookstand in the wing." "Clumsiness can be a very effective smokescreen." A silver tray of sourdough loaves slid onto the counter with a dull thud, sending a puff of flour into the air. "You're obsessing again. Eat your scone." "I can't eat when there's a thief in the village. Did you notice how he was fidgeting with his cufflinks?" "I noticed he looked like he needed a nap, just like you. Now, tell me—do you think the jam is too tart, or just right?" "Definitely too tart. Almost as tart as your skepticism."
created_at
"2026-05-10T12:43:15.234Z"
5/10/2026, 12:43:15 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
110
moderation_latency
(null)
generation_time
6760
tokens_prompt
81
tokens_completion
276
native_tokens_prompt
80
native_tokens_completion
253
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
0.00010654
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RF008aanxHYSTRX06DbiPwqf"
is_byok
false
latency
60
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-1778416995-8a0lzwB4DoX76Xz7ESVT"
session_id
(null)
api_type
"completions"
id
"gen-1778416995-xfmYEhgstMKu7qZjUEkC"
upstream_id
"chatcmpl-RF008aanxHYSTRX06DbiPwqf"
total_cost
0.00010654
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)