NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ09P1XH3S97ER2VVJWFE6DF
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2m 1s
Cost:
$0.000353
Provider:
Novita
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
"That first bite of almond tart, and the whole day feels brighter." "Your muffins always seem to know exactly what I need—soft, sweet, with a hint of lemon." "The oven's still humming; do you think the new rye will rise as promised?" "I heard Mrs. Dalloway's cat knocked over a sack of flour yesterday; the scent lingers." "Well, that explains the extra dust on the countertops. I was about to blame the wind." "Speaking of wind, the storm forecast says the power might flicker. Could we finish the pies before dark?" "If we keep the mixers humming, the batter will stay smooth. I’ll fetch the extra vanilla." "Don't forget the caramel drizzle; it's what keeps Mr. Harris coming back for his afternoon treat." "By the way, I found a handwritten note tucked under the sugar jar—'Meet me at the back door at six.'" "Sounds like a secret rendezvous. Perhaps it's just the town's way of adding mystery to our mornings." "Maybe the cat left more clues in the flour trail; we should follow it before it disappears." "Agree. And after that, a fresh loaf of sourdough should seal the mystery." "Until then, coffee will keep our thoughts warm."
created_at
"2026-04-24T17:47:58.779Z"
4/24/2026, 5:47:58 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
635
moderation_latency
(null)
generation_time
120628
tokens_prompt
81
tokens_completion
1412
native_tokens_prompt
130
native_tokens_completion
1386
native_tokens_completion_images
(null)
native_tokens_reasoning
1117
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
0.000353
router
(null)
provider_responses
0
endpoint_id
"3dc95f88-3960-4c91-b2bb-bbd2f5069c48"
id
"f4c1582b61118b40158b6c02867543ac"
is_byok
false
latency
523
model_permaslug
"openai/gpt-oss-120b"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777052878-73rbdS5IzvJHDwPlAW3J"
session_id
(null)
api_type
"completions"
id
"gen-1777052878-pgVKtttAwEVm6Y0Yceh6"
upstream_id
"f4c1582b61118b40158b6c02867543ac"
total_cost
0.000353
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)