NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXB3KXR0PE6JEHXYTX3EJ4
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.4s
Cost:
$0.013815
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
97.40%
Dialogue to Total Word Ratio
(details)
98.6981%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crouched behind the hedge, binoculars trained on the bouncy castle wobbling in the suburban backyard. Streamers fluttered. A clown juggled balloons with the desperate energy of a man who had not been paid. Beside her, Bill chewed a granola bar, dropping crumbs into the surveillance equipment. "This is our biggest score yet," he whispered. She lowered the binoculars and glared. The presents sat stacked on a folding table like a glittering Everest of wrapping paper and ribbon, guarded by nothing more menacing than a sleeping golden retriever and a grandmother dozing in a lawn chair. The plan was simple, which worried Molly, because Bill's plans were never simple for long. He had insisted on dressing as a magician, claiming the disguise would let them blend in. Currently he wore a top hat, a cape, and the haunted expression of a man whose fake mustache was peeling in the heat. A child shrieked nearby. Cake was being served. "Wait for the piƱata," Molly murmured. "Maximum chaos." Bill nodded solemnly, then pulled a dove from his sleeve, which immediately flew away, taking a chunk of his cape with it. Molly closed her eyes. Somewhere, professionally, she had taken a very wrong turn.
created_at
"2026-05-31T11:40:08.201Z"
5/31/2026, 11:40:08 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2687
moderation_latency
(null)
generation_time
9305
tokens_prompt
77
tokens_completion
384
native_tokens_prompt
93
native_tokens_completion
534
native_tokens_completion_images
(null)
native_tokens_reasoning
70
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
0.013815
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01YFDNejrULFNzUp8iEZ872o"
is_byok
false
latency
1183
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-1780227608-KwIafCou9vBGBtA67mMQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227608-84H6xHxlMtgH7kiac4zE"
upstream_id
"msg_01YFDNejrULFNzUp8iEZ872o"
total_cost
0.013815
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
97.40%
Dialogue to Total Word Ratio
Ratio: 5.97%, Deviation: 4.03%
neededClean
false
wordsTotal
201
wordsDialogue
12
98.6981%