NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91PVSSQ38B0R97EN7ME7E9
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
23.4s
Cost:
$0.000080
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 bell above the door gave a cheery chime, slicing through the warm, heavy scent of cinnamon and toasted pecans. "Is it true what they’re saying about the old Miller estate?" "I’m just here to sell scones, Clara, not discuss local real estate." "But the police were there all morning! I saw the blue sedan parked right by the ivy gate." "Perhaps they were just lost." "Not in those dark suits, they weren't. And the gardener? He looked like he’d seen a ghost." "Flour gets into everything, even the rumors. Do you want the blueberry ones or the lemon poppyseed today?" "Blueberry. And extra glaze. I’ll need the sugar to settle my nerves." "Coming right up." "Did you see him, though? The man in the charcoal coat wandering near the orchard?" "If I told you everything I saw, I’d never get the sourdough starter ready for the morning rush." "A mystery in Willow Creek... it’s about time something happened around here." "Just take your pastry. The tea is brewing in the back."
created_at
"2026-05-10T13:37:28.385Z"
5/10/2026, 1:37:28 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
280
moderation_latency
(null)
generation_time
23272
tokens_prompt
81
tokens_completion
3043
native_tokens_prompt
69
native_tokens_completion
231
native_tokens_completion_images
(null)
native_tokens_reasoning
2483
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
0.00008037
router
(null)
provider_responses
0
endpoint_id
"d99bcbe6-bec3-4991-965e-45fea79fe63c"
id
"chatcmpl-a14b0bca7cd54cb4"
is_byok
false
latency
280
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-1778420248-E0hv7IU2mCcaIEs99NUw"
session_id
(null)
api_type
"completions"
id
"gen-1778420248-1nqMLCdEkUhf5RvTnqxa"
upstream_id
"chatcmpl-a14b0bca7cd54cb4"
total_cost
0.00008037
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)