NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91AM346A4DDNF56DZQ6SGN
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 55s
Cost:
$0.000507
Provider:
Together
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 toasted cinnamon and warm yeast clung to the air, mingling with the fine dusting of flour that coated every surface of the countertop. Outside, the cobblestone streets of Oakhaven were just waking up, but inside the bakery, the ovens were humming a steady, comforting tune. "The lemon tarts look especially bright this morning." "I added a bit more zest. I needed the distraction." "Another restless night?" "I couldn't sleep. There was far too much commotion coming from the town square." "The square is always a circus on market days." "This wasn't market noise. Did you see the police cruisers huddled by the fountain?" "I’ve been frosting cupcakes since four. I haven't looked out the window once." "They’ve cordoned off the entire north side with yellow tape. Someone found something tangled in the ivy." "Please tell me it was just another stray cat." "A shoe. A very expensive, pointed red stiletto. Left right in the middle of the path, perfectly upright." "That certainly doesn't sound like a cat." "Exactly. And we both know exactly who in this town wears those."
created_at
"2026-05-10T13:30:47.275Z"
5/10/2026, 1:30:47 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
514
moderation_latency
(null)
generation_time
114505
tokens_prompt
81
tokens_completion
1054
native_tokens_prompt
82
native_tokens_completion
982
native_tokens_completion_images
(null)
native_tokens_reasoning
760
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
0.0005074
router
(null)
provider_responses
0
endpoint_id
"576fca5b-f09c-4bda-b560-9989c39ac3ab"
id
"oiXsaSr-zfFMX-9f994ceda5f653cb"
is_byok
false
latency
376
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778419847-PyQHtojaCu1924wWl1Xw"
session_id
(null)
api_type
"completions"
id
"gen-1778419847-GwZMoDBdKMffA8LGPJQX"
upstream_id
"oiXsaSr-zfFMX-9f994ceda5f653cb"
total_cost
0.0005074
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)