NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1G5JTF566G8CP6V7W5ESHS
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.6s
Cost:
$0.012290
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 blueprint across the hood of their van, smoothing it with both hands. "Okay, Bill, the bouncy castle is here," she said, tapping the paper. "That's our entry point." Bill squinted at the diagram. "Why are we going through a bouncy castle?" "Because nobody suspects a man crawling out of an inflatable dragon." "That's insane. We'll be visible to forty screaming children." "Children don't testify, Bill. That's chapter one of the handbook." He rubbed his temples. "We don't have a handbook." "We should. Anyway, the presents are stacked near the cake table, guarded only by a clown named Mr. Sprinkles." "A clown?" Bill paled. "You know I have a thing about clowns." "It's a children's party. Of course there's a clown." "Can't we steal from a quiet party? Like a funeral?" Molly stared at him. "Funerals don't have presents, you absolute amateur." "They have flowers." "We can't fence flowers!" Bill sighed, grabbing the smoke bombs. "Fine. But if Mr. Sprinkles so much as honks a nose at me, I'm out." "Deal," Molly grinned, pocketing two juice boxes for the road. "Now grab the loot bags. They're shaped like unicorns. Try to look festive." "I hate this job," Bill muttered.
created_at
"2026-06-01T11:47:38.964Z"
6/1/2026, 11:47:38 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1014
moderation_latency
(null)
generation_time
9545
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
93
native_tokens_completion
473
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
0.01229
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_017szLzHsYTvPmJFXtJytZH2"
is_byok
false
latency
1014
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-1780314458-qYO9PXTGmWLqHTrM9HuA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780314458-Whp3edoH63ZGkQWUPPNL"
upstream_id
"msg_017szLzHsYTvPmJFXtJytZH2"
total_cost
0.01229
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
0.00%
Dialogue to Total Word Ratio
Ratio: 74.13%, Deviation: 24.13%
neededClean
false
wordsTotal
201
wordsDialogue
149
49.9995%