NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ05BXDC4TBMMPH265SPJWK6
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.3s
Cost:
$0.001544
Provider:
SambaNova
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
96.23%
Dialogue to Total Word Ratio
(details)
98.1140%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 attic smelled of stale popcorn and old schematics, the perfect brainstorming nest for two under‑fed crooks. Molly paced, a pink polka‑dot cape fluttering behind her like a misguided superhero’s cape. Bill hunched over a hand‑drawn map of the community center, tracing the route from the delivery dock to the inflatable castle. He whispered, “Molly, you sure about the balloons?” as he lifted a glittery marker. Molly rolled her eyes, tapping a finger on the clipboard that listed “gift‑wrap, candy, squeaky toys”. “Bill, it’s a kids’ party, not a bank,” she muttered, adjusting a fake mustache that had been glued on hours earlier. He grinned, pointing at the inflatable slide that doubled as a covert ladder. “Just think of the candy tonight,” Bill said, eyes sparkling with the promise of sugar‑coated loot. The plan unfolded like a badly‑written children’s story: sneak past the clown, swap the gift bags for empty boxes, and slip away before the piñata exploded. A clock on the wall ticked down, each second a reminder that the party would begin in fifteen minutes, and the thieves could either make history or become the party’s next joke. They slipped into the night, humming “Take the Money and Run.”
created_at
"2026-04-24T16:32:32.183Z"
4/24/2026, 4:32:32 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1200
moderation_latency
(null)
generation_time
3176
tokens_prompt
77
tokens_completion
1588
native_tokens_prompt
127
native_tokens_completion
1607
native_tokens_completion_images
(null)
native_tokens_reasoning
1268
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
0.00154443
router
(null)
provider_responses
0
endpoint_id
"85835306-dba3-4334-87bc-ab9ffa5c9c62"
is_byok
false
latency
73
model_permaslug
"openai/gpt-oss-120b"
provider_name
"DeepInfra"
status
429
1
endpoint_id
"f487438c-e29a-408a-b38b-14045101a90d"
id
"b506af40-c512-4374-b72b-86df18ee414d"
is_byok
false
latency
1130
model_permaslug
"openai/gpt-oss-120b"
provider_name
"SambaNova"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777048352-aDBF3PZsm36YIlikcdDP"
session_id
(null)
api_type
"completions"
id
"gen-1777048352-V0QTidONNQi13pLrV2gS"
upstream_id
"b506af40-c512-4374-b72b-86df18ee414d"
total_cost
0.00154443
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
96.23%
Dialogue to Total Word Ratio
Ratio: 14.43%, Deviation: 4.43%
neededClean
false
wordsTotal
201
wordsDialogue
29
98.1140%