NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXJK8HKJ7ZHP0TDRP7DN12
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.1s
Cost:
$0.011990
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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 unfolded the blueprints across the hood of their rusty van, smoothing the wrinkled paper with both hands. "The bouncy castle is our blind spot," she said, tapping the diagram. "Nobody watches the perimeter when there's a bouncy castle." Bill squinted at the crayon-drawn map. "Did you steal these from a six-year-old?" "Borrowed them. From a six-year-old." He sighed, adjusting his clown costume. "Remind me why I'm dressed like this?" "Because clowns are invisible at parties," Molly explained. "You'll blend right in while I distract the parents with my magic act." "You don't know magic." "I know enough to make presents disappear." She grinned, sliding into her sequined cape. "That's all the magic we need, Bill." "And if the kids notice their gifts vanishing?" "Children have terrible memories. By cake time, they won't remember a thing." Bill honked his red nose nervously. "I've got a bad feeling about this." "You said that about the bank job." "We got arrested during the bank job!" Molly waved him off, gathering her props. "Minor setback. This time it's foolproof. Who suspects a magician and a clown?" "Everyone, Molly. Literally everyone suspects clowns." She paused, considering this. "Fair point. Grab the balloons anyway."
created_at
"2026-05-31T11:44:13.599Z"
5/31/2026, 11:44:13 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1414
moderation_latency
(null)
generation_time
10080
tokens_prompt
77
tokens_completion
338
native_tokens_prompt
93
native_tokens_completion
461
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
0.01199
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01D1imJL9pFQi9RRKnrPMYoV"
is_byok
false
latency
1414
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-1780227853-V3rkB92y7R6UJx3yMep6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227853-ecifqKcj1aRG6Vm66UJZ"
upstream_id
"msg_01D1imJL9pFQi9RRKnrPMYoV"
total_cost
0.01199
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
0.00%
Dialogue to Total Word Ratio
Ratio: 69.61%, Deviation: 19.61%
neededClean
false
wordsTotal
204
wordsDialogue
142
49.9995%