NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8V9NJT7F79CRZ5PDTYN4TC
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.6s
Cost:
$0.010910
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9595%
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
"So the party starts at two," Molly said, spreading a crayon-drawn map across the dashboard. "We go in through the back gate at two fifteen, right when they're doing the piñata." "Why the piñata?" Bill asked. "Because every kid and every parent will be blindfolded or ducking for cover. It's basically a war zone. Nobody's watching the gift table." "I don't know, Molly. Last time we hit a kid's party, that six-year-old bit me." "That was a birthday for twins. Twins are feral. This is a single-child event. Manageable." "And the presents? What are we expecting here?" "LEGOs, Bill. Mountains of LEGOs. There's also a rumor about a Nintendo Switch." "A rumor?" "I have a source inside the preschool. Very reliable. She goes by Princess Sparkle." "You're getting intel from a four-year-old?" "She drives a hard bargain. Cost me two juice boxes and a glitter sticker, but she delivered." Bill rubbed his temples. "What's our exit strategy?" "We load the wagon, roll out through the side yard, and blend in with the neighborhood dog walkers." "We don't have a dog." "That's why I stole one this morning." Bill stared at her. "You're a monster." "I prefer visionary."
created_at
"2026-02-24T22:11:13.634Z"
2/24/2026, 10:11:13 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1649
moderation_latency
157
generation_time
11371
tokens_prompt
77
tokens_completion
395
native_tokens_prompt
92
native_tokens_completion
418
native_tokens_completion_images
(null)
native_tokens_reasoning
72
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
0.01091
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"2f82e976-9c3a-44d6-9426-cc583b28468e"
is_byok
false
latency
1614
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971073-BD7GisIoGUpfvz4tn0h6"
upstream_id
"2f82e976-9c3a-44d6-9426-cc583b28468e"
total_cost
0.01091
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
100.00%
Dialogue to Total Word Ratio
Ratio: 90.15%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
183
99.9595%