NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8WQPETR2NWAV73JG7SC8SA
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.1s
Cost:
$0.000106
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 fresh lilies sitting on the marble counter. Outside, the cobblestone streets of Oakhaven were slick with a sudden autumn drizzle. "You can't be serious about the inheritance, Clara. It’s far too convenient." "Convenient? My uncle was a recluse who hated everyone. Leaving the estate to me is a miracle, not a conspiracy." "He didn't just leave you the house; he left you the secrets hidden in the cellar. I saw the way the lawyer looked at you." "You’re imagining things. Now, are you going to eat that lemon tart or just stare at it until it wilts?" "I can't eat. Not while the police are still asking questions about the tea service." "It was an accident. A slip of the hand, a misplaced sugar cube." "People don't just 'slip' and accidentally poison the town’s most eligible bachelor." "Hush. The baker is looking at us." "Let him look. This town has a memory like an elephant, and you’re wearing a very guilty expression."
created_at
"2026-05-10T12:10:32.802Z"
5/10/2026, 12:10:32 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
146
moderation_latency
(null)
generation_time
7951
tokens_prompt
81
tokens_completion
274
native_tokens_prompt
80
native_tokens_completion
252
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
0.00010616
router
(null)
provider_responses
0
endpoint_id
"9d4644e9-a5e5-41f4-b810-d75f484d2c24"
is_byok
false
latency
22
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Parasail"
status
429
1
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-R9edg1FkAGYmVuvu7AjbEEDN"
is_byok
false
latency
58
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-1778415032-cN6ugaPLKTKTem0TG3Jl"
session_id
(null)
api_type
"completions"
id
"gen-1778415032-QKXAVyoS4oBntaKcDI5L"
upstream_id
"chatcmpl-R9edg1FkAGYmVuvu7AjbEEDN"
total_cost
0.00010616
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)