NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HQ0SFCXF87HYVBBF57D4Y
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.5s
Cost:
$0.003122
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
89.12%
Dialogue to Total Word Ratio
(details)
93.9179%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 crouched behind the garden hedge, watching paper lanterns sway above the children’s party. Bill lay beside her, wearing a balloon hat that made stealth seem optimistic. “Once the magician arrives, we go in disguised as his assistants,” Molly whispered. “Which one of us knows magic?” “Neither. That’s why we’re assistants.” Bill peered through the leaves. “Those presents are enormous.” “Focus. We wheel them out during the cake distraction.” “What if someone asks where we’re taking them?” “The magician’s van.” “What if the magician asks?” “You tell him it’s part of the trick.” Bill adjusted his hat. It squeaked. Across the lawn, a little girl pointed directly at him. “She’s spotted us,” he said. “Then smile. You’re a balloon.” “I’m a man in a balloon hat.” “Keep smiling.” The girl marched over and held out a party invitation. “Are you the magician?” she asked. Molly stood. “His assistants. Where should we put the presents?” The girl considered this. “In the garage. Mum says we’re donating them after cake.” Bill blinked. “All of them?” “All of them.” Molly took the invitation. On the back, in cheerful capitals, it said CHARITY TOY DRIVE. “Brilliant,” Bill murmured. “We’re stealing from charity.” “Worse,” Molly said. “We volunteered to carry everything.”
created_at
"2026-09-23T16:31:21.916Z"
9/23/2026, 4:31:21 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5889
moderation_latency
(null)
generation_time
10498
tokens_prompt
75
tokens_completion
378
native_tokens_prompt
66
native_tokens_completion
299
native_tokens_completion_images
0
native_tokens_reasoning
0
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
"completed"
service_tier
"default"
usage
0.003122
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181081-wd4VlELdUegQtMrsF1zb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181081-Tjimyr7zEptpXl9rIznf"
upstream_id
"resp_0df538409482d734016ab3feda078087d1a325f15bb9f9522c"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0df538409482d734016ab3feda078087d1a325f15bb9f9522c"
is_byok
false
latency
4360
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.003122
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
89.12%
Dialogue to Total Word Ratio
Ratio: 55.83%, Deviation: 5.83%
neededClean
false
wordsTotal
206
wordsDialogue
115
93.9179%