NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ03RJNWGWVP2GE7MRHCZP31
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
38.9s
Cost:
$0.000294
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
"Did you hear that crash behind the flour bins?" "The only thing that could've moved that much is the cart, but it was locked." "Exactly, and the flour is still warm, as if someone just brushed it off." "I saw Mrs. Greene wiping her hands on the napkin, looking nervous." "She claimed she was just checking the cinnamon rolls, but why the sigh?" "The new batch of scones went missing, too. I counted them before you left." "Maybe the delivery boy slipped the tray? He was late this morning." "His shoes were muddy, but the floor was spotless when I stepped out." "The oven timer rang at the same moment—like a signal." "Did you notice the missing ledger? The one with the weekly expenses?" "It was on the counter, next to the cash box, and now it's gone." "I think someone used the back door; the cat was out, but the latch was bent." "Someone who knows the secret recipe—only the baker and a few trusted folks." "We should tell Sheriff Whitaker before the pastries are sold out." "The frosting on the cupcakes is still glossy, as if someone just applied it." "If we catch the culprit now, the town won't lose its sweet reputation."
created_at
"2026-04-24T16:04:30.023Z"
4/24/2026, 4:04:30 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
258
moderation_latency
(null)
generation_time
38742
tokens_prompt
81
tokens_completion
1434
native_tokens_prompt
115
native_tokens_completion
1522
native_tokens_completion_images
(null)
native_tokens_reasoning
1130
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
0.000293665
router
(null)
provider_responses
0
endpoint_id
"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id
"chatcmpl-Rmlj6IYNG6R3vMZm74zpFv2S"
is_byok
false
latency
77
model_permaslug
"openai/gpt-oss-120b"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777046670-C88rsF0fWQWRggzn59OX"
session_id
(null)
api_type
"completions"
id
"gen-1777046670-x5X4uCU2vFYRAdeVQlit"
upstream_id
"chatcmpl-Rmlj6IYNG6R3vMZm74zpFv2S"
total_cost
0.000293665
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)