NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA939NDK9AD7PNM5GVD6BX
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
44.7s
Cost:
$0.033703
Provider:
OpenAI
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
"So, we’re really robbing a children’s birthday party?" Molly whispered, peering over the backyard fence. Balloons bobbed like surveillance cameras made of rubber and bad decisions. "Aim high, Molly; the under-tens have the best loot." Bill adjusted his ski mask, which still had a price tag flapping. He crouched behind a hedge shaped like a dinosaur with regrets. "Last time we hit a casino." She brushed cupcake frosting off the blueprint. "And did you get a unicorn piñata, Bill? No. This is an upgrade." He pointed at the gift table sagging under glittery boxes. "Security?" she asked. "One clown, two exhausted parents, and a Labrador named Cupcake." Bill checked his watch as shrill music erupted. "Cupcake sounds dangerous." Molly eyed the dog gnawing a plastic tiara. "Only if you’re a sausage." Bill unfolded tiny walkie‑talkies decorated with stickers. "Focus: you distract the magician; I’ll grab the presents." He shoved one into her hand. "How exactly do I distract a magician?" she hissed. "Tell him you’re from the Union of Ethical Rabbits." Bill peeked through a gap in the fence. "And if that fails?" "Stage fright. Scream ‘card tricks exploit the vulnerable!’ and faint." "I’m not fainting near any balloons." Nearby.
created_at
"2026-02-16T13:30:31.462924+00:00"
2/16/2026, 1:30:31 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3870
moderation_latency
(null)
generation_time
44409
tokens_prompt
77
tokens_completion
1357
native_tokens_prompt
66
native_tokens_completion
3362
native_tokens_completion_images
0
native_tokens_reasoning
3057
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0337025
router
(null)
provider_responses
0
id
"resp_0530e9e502fe71b40169931bca1ec081908bcb5a54c8b03f41"
status
200
is_byok
false
latency
177
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248586-WYQzGZnur1XSIntkj6jG"
upstream_id
"resp_0530e9e502fe71b40169931bca1ec081908bcb5a54c8b03f41"
total_cost
0.0337025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
101
99.9995%