NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ09N5A11JWRNKQM6W4PAKFZ
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 39s
Cost:
$0.000544
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
63.25%
Dialogue to Total Word Ratio
(details)
81.6188%
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
The night sky glimmered above the backyard where the birthday balloons floated like bright planets, awaiting the stealthy duo musically. Molly: "We need a plan for the party." Bill: "Alright, what's the layout?" Molly: "Kids will be in the living room, balloons everywhere, cake table in the corner." Bill: "We slip in through the side gate, avoid the garden lights." Molly: "I bring the grappling hook, you disable the alarm with the jammer." Bill: "How long until the parents leave?" Molly: "Thirty minutes after the clown leaves, the kids will be distracted by the piñata." Bill: "Piñata—great cover, they’ll be busy swinging." Molly: "Then we grab the gift table, dump the boxes, and load them into the van." Bill: "What about the presents with stickers? We sort them later." Molly: "Exactly, we only need the boxes, the toys, the gadgets." Bill: "And the candy stash—big profit." Molly: "We split the loot fifty‑fifty, plus a bonus for whoever carries the most." Bill: "Deal. I’ll meet you at the trash bin at midnight." Molly: "See you then, partner in crime." Bill: "I'll bring the night-vision goggles; they hide us like shadows." Molly: "And I’ll wear the clown suit, nobody suspects a thief."
created_at
"2026-04-24T17:47:29.485Z"
4/24/2026, 5:47:29 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
265
moderation_latency
(null)
generation_time
98783
tokens_prompt
77
tokens_completion
2559
native_tokens_prompt
114
native_tokens_completion
2841
native_tokens_completion_images
(null)
native_tokens_reasoning
2231
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
0.000544236
router
(null)
provider_responses
0
endpoint_id
"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id
"chatcmpl-RcIb1xH7Byhr4837wbxcqfsC"
is_byok
false
latency
76
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-1777052849-2dcr7lULWFJ89wQ51Jg1"
session_id
(null)
api_type
"completions"
id
"gen-1777052849-T76lypuKfW0a7k6aZLG0"
upstream_id
"chatcmpl-RcIb1xH7Byhr4837wbxcqfsC"
total_cost
0.000544236
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
63.25%
Dialogue to Total Word Ratio
Ratio: 81.77%, Deviation: 8.23%
neededClean
false
wordsTotal
203
wordsDialogue
166
81.6188%