NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0AM3PJTSRPNYW5CM8M4TCK
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 23s
Cost:
$0.000875
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
97.09%
Dialogue to Total Word Ratio
(details)
98.2323%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly crouches behind the inflatable castle, Bill whispers from the snack table. Molly: "Okay, the party starts in fifteen, kids will be glued to the clown, perfect distraction." Bill: "Yeah, the clown's juggling knives—big mistake, they'll be too busy watching those." Molly: "We need the back door, the one that leads straight to the gift table." Bill: "Got it. I scoped the hallway; the sensor alarm is set for thirty seconds after motion." Molly: "Thirty seconds? We can sprint in, grab everything, and be out before the kids notice." Bill: "Our exit plan includes the puppy tunnel, you know, the one with the fake bone." Molly: "Brilliant. I’ll disable the lights with this tiny flashlight, you handle the door." Bill: "Fine, but watch the confetti cannon—once it fires, everyone will be covered in glitter." Molly: "That’s actually our advantage; they'll be too busy cleaning to notice missing presents." Bill: "I'll grab the candy stash as a backup if the gifts are locked." Molly: "Lock? Those gift boxes are just cardboard. Easy." Bill: "Alright, on my count—three, two, one—go!" Molly: "Leave the balloon arch; kids love it." Bill: "Perfect. Let’s make it unforgettable." Bill: "We vanish before the cake cutting." Lights dim.
created_at
"2026-04-24T18:04:23.646Z"
4/24/2026, 6:04:23 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
430
moderation_latency
(null)
generation_time
142918
tokens_prompt
77
tokens_completion
3425
native_tokens_prompt
129
native_tokens_completion
3473
native_tokens_completion_images
(null)
native_tokens_reasoning
3090
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
0.0008747
router
(null)
provider_responses
0
endpoint_id
"000e507a-4d52-4dee-927a-8ece3a7b0c28"
is_byok
false
latency
49
model_permaslug
"openai/gpt-oss-120b"
provider_name
"BaseTen"
status
429
1
endpoint_id
"3dc95f88-3960-4c91-b2bb-bbd2f5069c48"
id
"400e99b86aa9d2a0180b772556dd07f8"
is_byok
false
latency
347
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-1777053863-RpnZOf2JL7XfdBVt1BpK"
session_id
(null)
api_type
"completions"
id
"gen-1777053863-fAbUPloDT4l0lCKVEeNP"
upstream_id
"400e99b86aa9d2a0180b772556dd07f8"
total_cost
0.0008747
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
97.09%
Dialogue to Total Word Ratio
Ratio: 85.85%, Deviation: 4.15%
neededClean
false
wordsTotal
205
wordsDialogue
176
98.2323%