NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XB9X622ENXBYZAK549WQJ
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
20.3s
Cost:
$0.000086
Provider:
DekaLLM
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 cardamom and warm yeast clung to the air, thick enough to swallow the morning chill. Outside, a light dusting of snow began to blur the edges of the cobblestone street, but inside, the ovens hummed a comforting, rhythmic tune. "You’re staring at that lemon tart again as if it holds the secrets to the universe." "It might. Or it might just be the most distracting thing in this entire village." "The crust is a bit too golden for your liking?" "It’s perfect. It’s the flour dusting your apron that’s bothering me. You look like you’ve been wrestling with a cloud." "It was a heavy batch of sourdough. A messy business, really." "Speaking of messy, did you hear about the incident at the town hall last night?" "I try to avoid the local gossip, if only to preserve my sanity." "Even when it involves a missing ledger and a very suspicious amount of spilled ink?" "I heard nothing. I was far too busy perfecting this glaze." "Liars shouldn't drink tea so loudly. It's a dead giveaway." "It’s not lying. It’s selective hearing. There’s a profound difference."
created_at
"2026-05-10T12:21:15.309Z"
5/10/2026, 12:21:15 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8221
moderation_latency
(null)
generation_time
20268
tokens_prompt
81
tokens_completion
295
native_tokens_prompt
69
native_tokens_completion
247
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
0.00008565
router
(null)
provider_responses
0
endpoint_id
"d99bcbe6-bec3-4991-965e-45fea79fe63c"
id
"chatcmpl-8a5f0470cf654e1250a508d514477e15"
is_byok
false
latency
8221
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DekaLLM"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778415675-B7IApNZ4xCCmXuxsJMp9"
session_id
(null)
api_type
"completions"
id
"gen-1778415675-ga2K2cno767SwEFKkKTo"
upstream_id
"chatcmpl-8a5f0470cf654e1250a508d514477e15"
total_cost
0.00008565
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DekaLLM"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)