NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XSANB4BS6E469DP8EDRY3
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
22.7s
Cost:
$0.000102
Provider:
Parasail
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 yeast hung heavy in the air, thick enough to taste. Outside, the mist clung to the cobblestone streets of Willow Creek, but inside, the ovens provided a golden, buttery warmth. "You’re late. The sourdough starter is already peaking." "The bridge was flooded again. I had to take the long way around the orchard." "And you're soaking wet. You’ll catch a chill before the morning rush even begins." "Is that a lecture or an invitation to sit by the hearth?" "It's an observation. Now, grab those flour sacks. We have twelve dozen croissants to prep before the vicar arrives for his ritual scones." "Did you hear about the commotion at the old mill last night?" "I heard nothing but the wind. I don't care for gossip, only for crust and crumb." "It wasn't just wind. Someone broke the lock on the cellar door." "Then someone is looking for trouble, and trouble doesn't buy pastries. Put the apron on. We have work to do."
created_at
"2026-05-10T12:28:54.835Z"
5/10/2026, 12:28:54 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
469
moderation_latency
(null)
generation_time
22708
tokens_prompt
81
tokens_completion
254
native_tokens_prompt
80
native_tokens_completion
229
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
0.000102
router
(null)
provider_responses
0
endpoint_id
"91f05fe1-9a18-4bcf-8cfa-093c369d8cea"
id
"chatcmpl-954904a4a6cc3e8d"
is_byok
false
latency
469
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Parasail"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778416134-6GvVMXqmNrC8QUom90gm"
session_id
(null)
api_type
"completions"
id
"gen-1778416134-64f5IuGl9SCjbjRi4Pjw"
upstream_id
"chatcmpl-954904a4a6cc3e8d"
total_cost
0.000102
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)