NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8VW2GYG2GY6QNE02Z4ESFV
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
5.6s
Cost:
$0.000102
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 clung to the air, mingling with the soft chime of the bell above the door. Mrs. Gable adjusted her floral apron, her eyes narrowing as she leaned over the glass display of lemon tarts. "You’ve been staring at that sourdough for ten minutes, Arthur. Are you planning to buy it or perform an autopsy?" "I’m just wondering why the crust looks so... metallic." "It’s a sea-salt glaze. Now, move along. There’s a line forming behind you." "I saw him, Martha. I saw the Mayor slipping something into the flour bin before the morning rush." "Don't be absurd. The Mayor wouldn't know a flour bin from a birdbath." "He had a small glass vial. Clear liquid. He looked nervous, darting his eyes toward the clock." "You've been reading too many of those pulp novels. Now, do you want the rye or not?" "I want to know why the town accountant collapsed right after eating one of your specialty croissants." "He’s always had a weak stomach for butter."
created_at
"2026-05-10T11:55:27.654Z"
5/10/2026, 11:55:27 AM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
179
moderation_latency
(null)
generation_time
5526
tokens_prompt
81
tokens_completion
264
native_tokens_prompt
80
native_tokens_completion
241
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
0.00010198
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-ROPXMsZIVZrd9DNaSpbplWHF"
is_byok
false
latency
47
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-1778414127-chhbp3iPw0ACMtcJD5bu"
session_id
(null)
api_type
"completions"
id
"gen-1778414127-TnN1XNlConUf9gRL7B5t"
upstream_id
"chatcmpl-ROPXMsZIVZrd9DNaSpbplWHF"
total_cost
0.00010198
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)