NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1J48NDVAXHNTHEKXJJ4TKF
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.6s
Cost:
$0.014815
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 unfurled the blueprint across the hood of their getaway minivan, smoothing the crumpled corners with theatrical reverence. "Behold," she said. "The Henderson residence. Birthday party for little Timmy, age seven. Forty-three confirmed guests, twelve of them screaming." Bill squinted at the paper. "That's a placemat from a pancake house." "It's symbolic, Bill. Stay focused." She tapped a syrup stain. "The presents pile here, by the bouncy castle. We strike during the piñata." "Why the piñata?" "Because nobody watches presents when there's candy raining from the sky. Basic human nature." Bill scratched his chin nervously. "And the parents?" "Distracted, exhausted, possibly drunk. We waltz in dressed as clowns, grab the loot, and vanish before anyone notices." "I don't do clowns," Bill said flatly. "You know my history." "One traumatic birthday does not define a man." "It defines this man." Molly sighed, rolling up the placemat. "Fine. You'll be the magician. Cape, top hat, the works. You distract them with card tricks while I load the wagon." "I only know one card trick." "Then do it forty-three times!" Bill considered this, then nodded slowly. "We're really stealing from children." "Spoiled children," Molly corrected, grinning. "There's a moral difference, and frankly, we're heroes."
created_at
"2026-06-01T12:21:52.945Z"
6/1/2026, 12:21:52 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2999
moderation_latency
(null)
generation_time
10616
tokens_prompt
77
tokens_completion
402
native_tokens_prompt
93
native_tokens_completion
574
native_tokens_completion_images
(null)
native_tokens_reasoning
47
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
0.014815
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_014qbZriyJj58ZmHYPHiTnbV"
is_byok
false
latency
1142
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-1780316512-zSpcWKZWWclJaJcWxZV4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316512-NRI3f75vBnm9nJKLy7vG"
upstream_id
"msg_014qbZriyJj58ZmHYPHiTnbV"
total_cost
0.014815
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: 73.89%, Deviation: 23.89%
neededClean
false
wordsTotal
203
wordsDialogue
150
49.9995%