NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1G469YN7ZRM0Q2P9HH8PEG
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.8s
Cost:
$0.015515
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
77.39%
Dialogue to Total Word Ratio
(details)
88.3829%
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 hydrangeas, binoculars trained on the bouncy castle wobbling in the suburban backyard. Beside her, Bill struggled to squeeze his considerable frame into a clown costume two sizes too small, the seams whimpering with every breath. The plan, she reminded herself, was elegant in its simplicity. Slip in among the parents, blend into the chaos of frosting and screaming six-year-olds, and liberate the towering pyramid of wrapped gifts before anyone noticed. "Remember the signal," Molly whispered. Bill nodded, honking his nose accidentally. The signal, of course, was supposed to be a discreet tug of the ear, not the catastrophic horn now echoing across the lawn. A pack of children turned toward the bushes like tiny bloodhounds sensing weakness. Molly cursed under her breath, recalculating. Forty presents, maybe fifty, glittering and unguarded, surrounded by an army of sugar-crazed toddlers and one suspiciously alert golden retriever. She'd robbed banks. She'd cracked vaults in Monaco. None of it had prepared her for the horror of a piƱata swinging directly toward Bill's exposed forehead. "This is humiliating," Bill grumbled. Molly tightened her grip on the duffel bag, took a steadying breath, and decided that dignity, much like the presents, was simply another thing worth abandoning today.
created_at
"2026-06-01T11:46:53.381Z"
6/1/2026, 11:46:53 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3301
moderation_latency
(null)
generation_time
10785
tokens_prompt
77
tokens_completion
401
native_tokens_prompt
93
native_tokens_completion
602
native_tokens_completion_images
(null)
native_tokens_reasoning
57
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
0.015515
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_0124NftMsYuP6iCNXghW7rKo"
is_byok
false
latency
1105
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-1780314413-Ixh1OTuHBdpQOicbqvTm"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780314413-MzRRuWPWOVyGNA0Pecaw"
upstream_id
"msg_0124NftMsYuP6iCNXghW7rKo"
total_cost
0.015515
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
77.39%
Dialogue to Total Word Ratio
Ratio: 2.88%, Deviation: 7.12%
neededClean
false
wordsTotal
208
wordsDialogue
6
88.3829%