NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXJAZ1W5JVJV1QH9FH3XDP
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.2s
Cost:
$0.015190
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.89%
Dialogue to Total Word Ratio
(details)
99.9443%
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 hydrangea bush, binoculars trained on the suburban fortress decorated with balloons and crepe-paper streamers. Bill, meanwhile, was attempting to wrestle a clown costume over his considerable belly, the polyester straining against decades of questionable dietary choices. The plan, as Molly had explained it roughly forty times, was elegant in its simplicity: infiltrate the seventh birthday party of one Timothy Pennington, blend in among the parents, and abscond with the towering mountain of wrapped gifts before the candles were even lit. The garden swarmed with sugar-crazed children, their shrieks piercing the afternoon like tiny ungreased hinges. A bouncy castle wobbled ominously. Somewhere, a piƱata dangled, awaiting its violent destiny. "This is undignified," Bill grumbled, adjusting his rubber nose. Molly silenced him with a withering glare that could curdle milk at twenty paces. She had spent three weeks casing this operation, studying the parents' arrival patterns, the caterer's schedule, the precise moment the magician arrived to distract the masses with disappearing scarves. Bill honked his nose accidentally, startling a passing toddler. "Stay focused," she hissed. The presents glittered like Christmas itself, beckoning. Molly cracked her knuckles, smiled wickedly, and signaled the advance toward childhood's most poorly defended treasure trove.
created_at
"2026-05-31T11:44:05.101Z"
5/31/2026, 11:44:05 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6981
moderation_latency
(null)
generation_time
11183
tokens_prompt
77
tokens_completion
438
native_tokens_prompt
93
native_tokens_completion
589
native_tokens_completion_images
(null)
native_tokens_reasoning
77
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
0.01519
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01LJdanPcXcqg1ka5VLQ97io"
is_byok
false
latency
1068
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-1780227845-PvThAycITFIpea7soERi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227845-5aGhuvMl7HHJC4eJ79in"
upstream_id
"msg_01LJdanPcXcqg1ka5VLQ97io"
total_cost
0.01519
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
99.89%
Dialogue to Total Word Ratio
Ratio: 11.82%, Deviation: 1.82%
neededClean
false
wordsTotal
203
wordsDialogue
24
99.9443%