NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRA8P216TYW45PVP4RJCRG
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.3s
Cost:
$0.013190
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
67.81%
Dialogue to Total Word Ratio
(details)
71.4827%
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
"Right," said Molly. "Cake at three, piñata at three-fifteen, presents at four." "So we hit it at three-fifteen." "We hit it at three-fifteen." "During the piñata." "During the piñata, Bill." "Molly, that's twelve blindfolded children swinging a bat in a confined space." "That's the beauty of it. Nobody's looking. Everybody's screaming." "I'll be screaming." "You'll be fine. You're going in as the magician." "I don't know any magic." "You know the one with the coin." "I lose the coin. Every time. That's not a trick, that's just misplacing money in front of an audience." "Then be a bad magician. Children love a bad magician. They'll heckle you, and while they're heckling you, I'm out the patio door with forty pounds of unopened Lego." "And the parents?" "Filming you. Vertically." "That's my face on the internet, Molly." "You'll be wearing the hat." "The hat isn't a disguise, it's a hat." "It's a very large hat." "What about the dog?" "What dog?" "They've got a dog, Molly. Big one. Name's Duchess." "Duchess gets the sausages." "Duchess gets the sausages," Bill sighed. "And what do I get?" "Applause, Bill. Possibly."
created_at
"2026-07-25T13:44:27.084Z"
7/25/2026, 1:44:27 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3649
moderation_latency
(null)
generation_time
9095
tokens_prompt
75
tokens_completion
341
native_tokens_prompt
93
native_tokens_completion
509
native_tokens_completion_images
(null)
native_tokens_reasoning
39
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
0.01319
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNskKTYM2JWwbRTvN9Vi"
is_byok
false
latency
1170
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-1784987067-yRgyIbfA2CRD1Uk9I0ko"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987067-xwdzd1pBJJycwKLiEUj1"
upstream_id
"msg_011CdNskKTYM2JWwbRTvN9Vi"
total_cost
0.01319
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
75.16%
Matches word count
n/a
neededClean
false
words
187
67.81%
Dialogue to Total Word Ratio
Ratio: 97.89%, Deviation: 7.89%
neededClean
false
wordsTotal
190
wordsDialogue
186
71.4827%