NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1HNWKEP88WDA7291283WRR
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.5s
Cost:
$0.012765
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
78.33%
Dialogue to Total Word Ratio
(details)
89.1585%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"So we're really doing this?" Molly asked. "Robbing a kid's birthday party?" "Not robbing. Liberating," Bill said. "Those presents are practically begging to be stolen." "From a six-year-old." "From a *spoiled* six-year-old. Did you see the invitation? 'Bouncy castle, pony rides, and a chocolate fountain.' That's excessive." "And our plan is?" "You distract everyone as the clown." "Absolutely not." "Molly, you're a natural. The big shoes, the red nose—" "I'm not wearing the nose." "Fine. No nose. But you've got to juggle something." "I can't juggle." "Then throw the things and catch them dramatically. Nobody at a kid's party expects competence." "And what'll you be doing while I'm humiliating myself?" "Loading the loot into the van. We hit the present table, grab everything, and we're gone before they sing 'Happy Birthday.'" "This is the worst plan you've ever had." "It's foolproof! Who suspects a clown?" "Everyone. Everyone suspects the clown." "Look, the kid's got two hundred guests. That's two hundred presents. We could retire." "On secondhand action figures and gift cards?" "There's always cash in those little envelopes." Molly sighed. "If I get hit with a piñata stick, I'm leaving you behind." "Deal. Now put on the shoes."
created_at
"2026-06-01T12:14:01.845Z"
6/1/2026, 12:14:01 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2015
moderation_latency
(null)
generation_time
10440
tokens_prompt
77
tokens_completion
350
native_tokens_prompt
93
native_tokens_completion
492
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
0.012765
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01CPYphPtiMmJwzTF6H9ewMp"
is_byok
false
latency
2014
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-1780316041-g1vev96HsHBTgoSMQLnd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316041-S3bUxRFriPUGyd0y84Tt"
upstream_id
"msg_01CPYphPtiMmJwzTF6H9ewMp"
total_cost
0.012765
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
78.33%
Dialogue to Total Word Ratio
Ratio: 97.03%, Deviation: 7.03%
neededClean
false
wordsTotal
202
wordsDialogue
196
89.1585%