NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91RECVK16Y4G3Z8XE87CCA
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
40.7s
Cost:
$0.000139
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 cinnamon and warm yeast clung to the air, mingling with the floral notes of a fresh bouquet of peonies on the counter. Outside, the cobblestone streets of Willow Creek were dusting with a light autumn rain. "I’m telling you, the icing was far too blue." "It’s a celebration cake, Martha. It’s supposed to be vibrant." "There is a difference between vibrant and radioactive. It practically glowed under the parlor lights." "It was a custom request. The client wanted 'Electric Azure.'" "Well, the client has questionable taste. And besides, did you notice how Mrs. Higgins looked at it? She didn't touch a single slice." "Maybe she was just full from the finger sandwiches." "Or maybe she suspected it was poisoned. I saw her whispering to the vicar right after the toast." "You have a flair for the dramatic that borders on the exhausted." "It’s not drama when there’s a suspicious amount of almond extract involved." "It’s a wedding cake, not a crime scene." "In this town, dear, they are often one and the same."
created_at
"2026-05-10T13:38:20.202Z"
5/10/2026, 1:38:20 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
845
moderation_latency
(null)
generation_time
40359
tokens_prompt
81
tokens_completion
281
native_tokens_prompt
80
native_tokens_completion
245
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
0.0001385
router
(null)
provider_responses
0
endpoint_id
"29b94af5-d8f8-419a-9cf1-ae1f2831142b"
is_byok
false
latency
207
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Venice"
status
429
1
endpoint_id
"69279254-6a96-4e9d-abc6-ea76e6bf8e97"
is_byok
false
latency
92
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Novita"
status
429
2
endpoint_id
"576fca5b-f09c-4bda-b560-9989c39ac3ab"
id
"oiXuuJ6-zfFMX-9f995800e08c091a"
is_byok
false
latency
845
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-1778420300-W59ICeNXKWjvZAe1UZhe"
session_id
(null)
api_type
"completions"
id
"gen-1778420300-NLRehUMNzez3YGlm5kiW"
upstream_id
"oiXuuJ6-zfFMX-9f995800e08c091a"
total_cost
0.0001385
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)