NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJY8VF2Q6X4XGS187Y5Z27
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.7s
Cost:
$0.014915
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
77.54%
Dialogue to Total Word Ratio
(details)
88.7715%
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 sagged from the gutters, and a clown honked his way through a crowd of sugar-crazed seven-year-olds. The presents sat stacked on a folding table like a glittering monument to childhood greed, ribbons fluttering in the breeze. Bill adjusted his stolen party hat, the elastic strap biting cruelly into his stubbled chins. He'd insisted on the disguise, claiming nobody suspected a man dressed as a birthday guest. The fact that he was forty-six and uninvited had not factored into his calculations. "This is foolproof," he whispered, gesturing with a half-eaten cupcake. Molly rolled her eyes. The clown was the real threat, she decided, watching him juggle with unsettling precision. A professional. Possibly former military. She mapped their route mentally: slip past the piƱata, dodge the face-painting station, grab the gift table, and vanish before the cake arrived. Twelve seconds, maximum. The getaway van idled in the alley, its engine purring beneath a magnetic sign reading PARTY SUPPLIES PLUS. "Remember the plan," she murmured. Bill nodded solemnly, frosting smeared across his nose, having already forgotten every single detail they'd rehearsed for three exhausting, miserable weeks straight.
created_at
"2026-05-29T10:02:09.659Z"
5/29/2026, 10:02:09 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2977
moderation_latency
(null)
generation_time
10666
tokens_prompt
77
tokens_completion
386
native_tokens_prompt
93
native_tokens_completion
578
native_tokens_completion_images
(null)
native_tokens_reasoning
44
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
0.014915
router
(null)
provider_responses
0
endpoint_id
"dfc0e5bd-d703-4fe2-a7bb-655eb95d5441"
id
"msg_01QzLVWY8b5ZbofAxdwKCG5M"
is_byok
false
latency
1079
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-1780048929-mDDgwWnACeN8bOQkktRl"
session_id
(null)
api_type
"completions"
id
"gen-1780048929-eWVAaCCuXlxJPtezjVAg"
upstream_id
"msg_01QzLVWY8b5ZbofAxdwKCG5M"
total_cost
0.014915
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
77.54%
Dialogue to Total Word Ratio
Ratio: 2.90%, Deviation: 7.10%
neededClean
false
wordsTotal
207
wordsDialogue
6
88.7715%