NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJFYEV0JGR7KEYC3XFF0JY
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.3s
Cost:
$0.013240
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.08%
Dialogue to Total Word Ratio
(details)
99.5378%
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 we're really doing this?" Bill asked. "Stealing from kids?" "Not kids. Presents," Molly said. "There's a difference." "What difference?" "The presents won't cry when we take them." "The kids will." "Then we work fast," she said. "In and out before the cake." "What's the plan?" "You distract them. I grab the loot." "How do I distract a dozen seven-year-olds?" "You're dressed as a clown, Bill. Clown around." "I hate clowning." "Nobody hates clowning." "I do. Deeply. It's why I left the circus." "You left the circus because you stole the elephant." "Borrowed." "You can't borrow an elephant!" "I gave it back!" "To the wrong zoo!" Bill crossed his arms. "Fine. I'll clown. But you owe me." "I'll buy you a balloon animal." "I want a real animal." "We are not stealing another elephant." "A goldfish, then." "Deal," Molly said. "Now, when I signal, you do the honking nose thing." "I don't have a honking nose." "Then honk verbally." "That's humiliating." "So is prison, Bill. Honk for freedom." He sighed. "Honk." "Louder." "HONK." "Perfect. The presents won't know what hit them." "And the kids?" "They'll remember this birthday forever." "That's the saddest thing you've ever said." "Get in the van, Bonkers."
created_at
"2026-05-29T09:54:20.262Z"
5/29/2026, 9:54:20 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1275
moderation_latency
(null)
generation_time
10302
tokens_prompt
77
tokens_completion
366
native_tokens_prompt
93
native_tokens_completion
511
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)
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
0.01324
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_011RNhTrH48N2rBJqs5sB2F3"
is_byok
false
latency
1273
model_permaslug
"anthropic/claude-4.8-opus-20260528"
provider_name
"Anthropic"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780048460-i7CryGVRVPJc33oHB3oX"
session_id
(null)
api_type
"completions"
id
"gen-1780048460-D59Aw0BOuhhoeY7VTjmJ"
upstream_id
"msg_011RNhTrH48N2rBJqs5sB2F3"
total_cost
0.01324
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
99.08%
Dialogue to Total Word Ratio
Ratio: 93.10%, Deviation: 3.10%
neededClean
false
wordsTotal
203
wordsDialogue
189
99.5378%