NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJYYPAXFZ1Y76T88PEDFW1
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.6s
Cost:
$0.014565
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
98.95%
Dialogue to Total Word Ratio
(details)
99.4354%
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. Balloons bobbed. Somewhere inside that pastel fortress lay a mountain of gift-wrapped treasure, and she intended to claim every glittering box of it. Bill adjusted his clown wig, sweating beneath the polyester. He had insisted the disguise was foolproof, despite the fact that his fake nose kept sliding into his mustache, which was also fake, and also sliding. He looked less like a party entertainer and more like a hostage situation. "The cake table's our extraction point," Molly whispered. Bill nodded gravely, then squeezed his honking nose for confidence. The plan was elegant in its simplicity. Bill would distract the children with balloon animals while Molly slipped through the back gate, loaded the presents into a deflated piƱata, and vanished before the candles were lit. Twelve toddlers stood between them and untold riches in action figures and pony-themed merchandise. "Remember," she added, "no eye contact with the birthday girl." A whistle blew. The face-painting station opened. Somewhere a parent uncorked sparkling cider, and the operation commenced. Bill stumbled forward into the fray, honking, juggling, terrified, while Molly melted into the shrubbery, grinning like a professional.
created_at
"2026-05-29T10:02:32.017Z"
5/29/2026, 10:02:32 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2856
moderation_latency
(null)
generation_time
10616
tokens_prompt
77
tokens_completion
400
native_tokens_prompt
93
native_tokens_completion
564
native_tokens_completion_images
(null)
native_tokens_reasoning
54
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
0.014565
router
(null)
provider_responses
0
endpoint_id
"dfc0e5bd-d703-4fe2-a7bb-655eb95d5441"
id
"msg_01RZzt5K9Nhsnb7ebo1HoMi7"
is_byok
false
latency
1025
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-1780048952-NAK9TqYiVaUt0mLFzixg"
session_id
(null)
api_type
"completions"
id
"gen-1780048952-vS0l8I9dxzslhDAVAozK"
upstream_id
"msg_01RZzt5K9Nhsnb7ebo1HoMi7"
total_cost
0.014565
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
98.95%
Dialogue to Total Word Ratio
Ratio: 6.80%, Deviation: 3.20%
neededClean
false
wordsTotal
206
wordsDialogue
14
99.4354%