NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.6
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYZK24BS8R1X4WXZGDRB3ES
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
Molly spread the hand-drawn blueprint across the sticky diner table, knocking over a bottle of ketchup in the process. The map showed a suburban backyard in meticulous detail, complete with a bounce house, a balloon arch, and what appeared to be a very aggressive piƱata hanging from an oak tree. She had spent three days conducting surveillance from behind a neighbor's hedge, enduring two sprinkler attacks and one unfortunate encounter with a territorial garden gnome. Bill studied the layout while nervously shredding a napkin into confetti. His last job had been lifting wallets at a county fair, and even that had ended with him fleeing from a surprisingly fast grandmother in orthopedic shoes. This felt like a significant escalation. "We go in during cake time," Molly whispered, tapping the garage where the presents would be stashed. "Every kid and parent will be hypnotized by sugar. We'll have four minutes, maybe five." "What about the dog?" Bill asked. "Goldendoodle. Practically an accomplice. I've been feeding him salami through the fence all week." Bill exhaled slowly. Somewhere in his chest, a tiny voice suggested he reconsider his life choices. He ignored it, as usual. "Saturday then," he said. Molly grinned and rolled up the blueprint.
created_at
"2026-02-08T15:58:18.959014+00:00"
Sunday, February 8th, 2026 at 3:58:18 PM GMT+00:00
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1452
moderation_latency
168
generation_time
8644
tokens_prompt
61
tokens_completion
261
native_tokens_prompt
75
native_tokens_completion
303
native_tokens_completion_images
(null)
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00795
router
(null)
provider_responses
0
id
"159e1e86-cdb8-4916-8a85-cf2292e296cc"
status
200
is_byok
false
latency
1452
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770566289-WGAhgWUiOSq2m4RZM50a"
upstream_id
"159e1e86-cdb8-4916-8a85-cf2292e296cc"
total_cost
0.00795
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
35.3527%
Dialogue to Total Word Ratio
Ratio: 20.10%, Deviation: 10.10%
neededClean
false
wordsTotal
204
wordsDialogue
41
67.5485%