NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJJQ8E92J8YNEAMZJK72CS
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.0s
Cost:
$0.011965
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
93.71%
Dialogue to Total Word Ratio
(details)
96.8523%
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?" Molly asked. "Robbing children?" "Not robbing children," Bill said. "Robbing presents. Big difference." "How is that different?" "The children don't pay for the presents. So technically, we're robbing the parents." "The parents who love their children." "Look, do you want to eat this month or not?" "I want to eat," Molly admitted. "I just don't want to make a six-year-old cry." "Then we wait until after the cake. They're too sugar-high to notice anything." "That's your plan? Sugar?" "That's half my plan. The other half is the bouncy castle." "What does the bouncy castle do?" "Distraction. Nobody watches the present table when there's a bouncy castle." "And how do we get in?" "I'm the magician. You're my assistant." "I'm not wearing a sequined leotard, Bill." "You'll wear what the act demands." "The act demands dignity." "The act demands sequins." "What if they ask you to do real magic?" "I pull a rabbit from a hat. I've practiced." "You have a rabbit?" "I have a hat. The rabbit's a work in progress." "This is going to fail spectacularly." "Probably," Bill agreed. "But think of the presents." "Fine," Molly sighed. "But I'm keeping the bouncy castle."
created_at
"2026-05-29T09:55:51.192Z"
5/29/2026, 9:55:51 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1344
moderation_latency
(null)
generation_time
8996
tokens_prompt
77
tokens_completion
342
native_tokens_prompt
93
native_tokens_completion
460
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
0.011965
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01K2u3dPcnMsDyyWbPyGY84n"
is_byok
false
latency
1344
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-1780048551-knX0EBrt2LZxg0MDx4dl"
session_id
(null)
api_type
"completions"
id
"gen-1780048551-YKeU5iUG0XKsQcsDLzUu"
upstream_id
"msg_01K2u3dPcnMsDyyWbPyGY84n"
total_cost
0.011965
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
199
93.71%
Dialogue to Total Word Ratio
Ratio: 95.05%, Deviation: 5.05%
neededClean
false
wordsTotal
202
wordsDialogue
192
96.8523%