NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ03F7SJQ4PYN5EBMNWJE5MV
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
29.0s
Cost:
$0.000155
Provider:
SiliconFlow
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
“Did you notice the flour dust on the counter this morning? It’s not from the new batch.” “Exactly. And the cookie tin—gone. The one with the little blue ribbon.” “Someone must’ve slipped it into the mixer. That would explain the odd taste in the scones.” “I tasted it. A hint of cinnamon, but also… something metallic.” “The baker’s apprentice said he saw a stranger linger by the window, staring at the display.” “Was it the same stranger who left that note on the register? ‘Meet me at midnight, behind the oak.’?” “Only one way to find out.” “Should we tell Mrs. Whitaker? She’s been nervous since the missing recipe book.” “She’ll want to know, but she prefers the dough to stay calm.” “Then we’ll keep watch. I’ll bring the lantern; you take the spare key.” “Deal. If we’re lucky, the culprit will think the bakery’s just a pleasant place to hide.” “Or they’ll realize the town’s already smelled the truth.” “Either way, I’ll bake a fresh batch—no secrets in the sugar.” “Let’s hope the mystery dissolves before the next delivery.”
created_at
"2026-04-24T15:59:23.965Z"
4/24/2026, 3:59:23 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3699
moderation_latency
(null)
generation_time
28953
tokens_prompt
81
tokens_completion
390
native_tokens_prompt
128
native_tokens_completion
330
native_tokens_completion_images
(null)
native_tokens_reasoning
72
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"
usage
0.0001549
router
(null)
provider_responses
0
endpoint_id
"ce118593-d9b2-4d2d-bcd4-33f0609b42f1"
id
"019dc037a4ef3c11078b27218e83867c"
is_byok
false
latency
3335
model_permaslug
"openai/gpt-oss-120b"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777046363-AUOjcDc3EOJjEJiTXuZS"
session_id
(null)
api_type
"completions"
id
"gen-1777046363-EPneOhzwr1z1iKsIYbRW"
upstream_id
"019dc037a4ef3c11078b27218e83867c"
total_cost
0.0001549
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)