NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR5V94FJX9QANJ96D7P898
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
15.6s
Cost:
$0.018415
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
93.23%
Dialogue to Total Word Ratio
(details)
96.6068%
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
Molly unrolled the blueprint across the hood of the van, smoothing it with the reverence of a surgeon, though it was actually a place mat from a pizzeria with a bouncy castle drawn on it in eyeliner. Bill leaned in, chewing a licorice rope he had stolen from a gas station as a warm-up exercise. The plan was elegant. The presents would be stacked on a folding table beneath the gazebo, unguarded except by a grandmother who, according to three days of surveillance, fell asleep sometime around the second round of pin the tail on the donkey. Molly had timed it. Forty-one minutes of viable extraction window, assuming the cake came out on schedule. "Twelve kids," she said. "Maybe fourteen. And one clown." Bill stopped chewing. His face did something complicated. "I hate clowns," he said. She ignored him and tapped the eyeliner sketch, indicating the hedge where they would stash the wheelbarrow. Costumes were in the back: two enormous foam dinosaurs, purchased legitimately, which felt like a betrayal of their principles. Bill's had a broken zipper. Molly's smelled of another man's ambition. Somewhere across town, a seven-year-old named Dexter was blowing up balloons, blissfully unaware, and Molly almost felt guilty. Almost.
created_at
"2026-07-25T13:42:02.283Z"
7/25/2026, 1:42:02 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5531
moderation_latency
(null)
generation_time
15467
tokens_prompt
75
tokens_completion
382
native_tokens_prompt
93
native_tokens_completion
718
native_tokens_completion_images
(null)
native_tokens_reasoning
68
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
"end_turn"
service_tier
"default"
usage
0.018415
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsZfdBK6efYtbSfdyqE"
is_byok
false
latency
2648
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784986922-qj1efsyD8caxOUpQXBnZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986922-R4U9oIas9V4OYM6RpGDl"
upstream_id
"msg_011CdNsZfdBK6efYtbSfdyqE"
total_cost
0.018415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
93.23%
Dialogue to Total Word Ratio
Ratio: 4.85%, Deviation: 5.15%
neededClean
false
wordsTotal
206
wordsDialogue
10
96.6068%