NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJEQQS17JQW98EDKWDNCQF
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.7s
Cost:
$0.014815
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 spread the blueprints across the table, smoothing them with reverent care. They were drawn in crayon. "The bouncy castle is our entry point," she said, tapping it. "Security's lax around the inflatables." Bill squinted. "Why's the cake circled in red?" "That's the diversion. While they're singing, we slip in through the ball pit and grab the gift table." "There's a clown," he whispered, pointing. "I hate clowns, Molly." "Everyone hates clowns. That's why nobody watches them. He's perfect cover." Bill rubbed his temples. "We're forty-two years old. We rob banks. Why are we stealing a six-year-old's presents?" "Because," Molly said, eyes gleaming, "nobody suspects the catering staff. And little Timothy's parents are loaded. There's a PlayStation in that pile. Possibly two." "And the piƱata?" "Insurance. We bust it open, candy goes everywhere, chaos erupts, and we walk out with the loot disguised as party favors." Bill considered this for a long, troubled moment. "What if they make us wear name tags?" "Then we wear name tags," she snapped. "Honestly, Bill, where's your professionalism?" "My professionalism doesn't usually involve juice boxes and face painting." Molly stood, slinging her bag over her shoulder. "Grab the balloons. We're going to a party."
created_at
"2026-05-29T09:53:40.609Z"
5/29/2026, 9:53:40 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3258
moderation_latency
(null)
generation_time
10708
tokens_prompt
77
tokens_completion
396
native_tokens_prompt
93
native_tokens_completion
574
native_tokens_completion_images
(null)
native_tokens_reasoning
53
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
0.014815
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01DuotXGuFnAV2kvg84E8Yym"
is_byok
false
latency
1680
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-1780048420-u63NoFZp5BLS03nWPyEN"
session_id
(null)
api_type
"completions"
id
"gen-1780048420-KDvNKXDY8O42UnKPUv1j"
upstream_id
"msg_01DuotXGuFnAV2kvg84E8Yym"
total_cost
0.014815
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
200
0.00%
Dialogue to Total Word Ratio
Ratio: 74.38%, Deviation: 24.38%
neededClean
false
wordsTotal
203
wordsDialogue
151
50.0000%