NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XDNFMX8SRA0TT02Y85E4E
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
34.6s
Cost:
$0.001210
Provider:
Cloudflare
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 cheerful jingle, slicing through the heavy, comforting scent of toasted cinnamon and warming yeast. A fine dusting of flour hung suspended in the shafts of morning sunlight, dancing over the display cases of glazed pastries and braided brioche. "The lavender scones are just coming out of the oven." "They look divine, but I’m really here for the gossip." "Is it about the Mayor’s gala? I heard the caterers pulled out at the last minute." "Worse. Someone broke into the library last night." "Oh, goodness. Not the rare manuscripts section? Not after all that hard work on the renovation?" "Exactly. And it wasn't just a common smash-and-grab. They left something behind." "A note? A calling card?" "A single, powdery white fingerprint. Right on the glass of the nineteenth-century poetry collection." "Flour? In the library?" "Precisely. It’s as if they walked straight from a kitchen into a crime scene." "Well, that certainly puts a damper on my morning blueberry muffin." "Maybe I should check my pantry for any missing ingredients."
created_at
"2026-05-10T12:22:32.7Z"
5/10/2026, 12:22:32 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
937
moderation_latency
(null)
generation_time
34470
tokens_prompt
81
tokens_completion
3718
native_tokens_prompt
82
native_tokens_completion
4005
native_tokens_completion_images
(null)
native_tokens_reasoning
3427
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
0.0012097
router
(null)
provider_responses
0
endpoint_id
"e2a16fa6-1f65-413e-9ecb-93901089ddb1"
id
"id-1778415753095"
is_byok
false
latency
403
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Cloudflare"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778415752-qKrpNbtvDlPdXxI2zCS3"
session_id
(null)
api_type
"completions"
id
"gen-1778415752-FNh9kUpcjhtmiFqhnHoL"
upstream_id
"id-1778415753095"
total_cost
0.0012097
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)