NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ07XBYPJ6XB3G35GDNMQXC9
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
22.2s
Cost:
$0.000168
Provider:
Io Net
Evaluation summary
Score
Evaluator
Details Link
13.53%
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 over the bakery door jingled as the late‑morning crowd thinned. Sunlight sifted through the lace‑curtained windows, casting a honeyed glow on the half‑eaten scones stacked on the counter. “Did you hear about the old Miller place on Oak?”
a voice asked
, thin and curious, as a steaming cup of tea clinked against a porcelain saucer. “Someone mentioned that the garden’s been fenced off for good,”
the other replied
, wiping crumbs from a flour‑dusted cheek. “Rumor has it there’s a hidden cellar.” “Hidden cellar? In Miller’s house? That’s the kind of story that makes the town gossip mill spin faster than the mixer.” “Alice always says mystery follows the scent of fresh bread. Maybe we should investigate after the last batch is sold.” “Just think—if there’s a secret room, the cookies might be the only thing keeping it quiet.” A soft chuckle rose from the back where a wedding cake rested, its layers gleaming. The baker, wiping her hands on a towel, glanced up and smiled, her eyes twinkling with unspoken agreement. The two lingered over their pastries, the bakery humming with the promise of another mystery to uncover.
created_at
"2026-04-24T17:17:01.293Z"
4/24/2026, 5:17:01 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
548
moderation_latency
(null)
generation_time
21973
tokens_prompt
81
tokens_completion
516
native_tokens_prompt
130
native_tokens_completion
436
native_tokens_completion_images
(null)
native_tokens_reasoning
205
native_tokens_cached
64
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
0.000168327
router
(null)
provider_responses
0
endpoint_id
"aa7799a4-4935-4de1-9cb3-8ebf9c1cf4e3"
id
"chatcmpl-650fe5e6-fef5-468d-86b2-d99995424960"
is_byok
false
latency
548
model_permaslug
"openai/gpt-oss-120b"
provider_name
"Io Net"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777051021-J3W6GZ4bI0kA0WaUjR3u"
session_id
(null)
api_type
"completions"
id
"gen-1777051021-pN5trDBhKTIButCgmrmY"
upstream_id
"chatcmpl-650fe5e6-fef5-468d-86b2-d99995424960"
total_cost
0.000168327
cache_discount
0.00000576
upstream_inference_cost
0
provider_name
"Io Net"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
13.53%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"a voice asked"
1
"the other replied"