NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJRZ6E4Y65RCZ7S8SSB53H
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.3s
Cost:
$0.013665
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 spread the blueprint across the table, smoothing its wrinkled corners. "The bouncy castle is here. That's our entry point." Bill squinted. "We're crawling through a bouncy castle?" "Through it, under it, around it. Whatever it takes." "And the guards?" "Two clowns and a magician," Molly said. "The magician's the dangerous one." Bill laughed nervously. "Dangerous how? He's gonna pull a rabbit on us?" "Don't underestimate close-up magic, Bill. The man can palm a quarter. Imagine what he does with handcuffs." Bill swallowed hard, tapping the diagram. "What about the loot? Where do they stash the presents?" "Pile in the corner. Wrapped, bowed, completely unguarded except for one thing." "Which is?" "Forty screaming six-year-olds hopped up on birthday cake." Bill paled. "That's a war zone." "That's an opportunity," Molly corrected. "Chaos is our friend. We move during the piñata." "The piñata?" "Blindfolds, swinging bats, candy raining down. Total pandemonium." She grinned. "Nobody's watching the gift table when free candy's involved." Bill rubbed his temples. "Molly, we've robbed banks. Casinos. Now we're stealing from toddlers?" "Those toddlers," Molly said coldly, "have a brand-new gaming console in that pile. Retail value, four hundred bucks." Bill's eyes lit up. "When's the party?"
created_at
"2026-05-29T09:59:15.929Z"
5/29/2026, 9:59:15 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1262
moderation_latency
(null)
generation_time
10285
tokens_prompt
77
tokens_completion
359
native_tokens_prompt
93
native_tokens_completion
528
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
0.013665
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_017Rr5Q6dxGNAhECkC7LsdTN"
is_byok
false
latency
1262
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-1780048755-KmULBNU8Nj5ylHBVNTpM"
session_id
(null)
api_type
"completions"
id
"gen-1780048755-PtkQsZ8GAlcjJkrZe71k"
upstream_id
"msg_017Rr5Q6dxGNAhECkC7LsdTN"
total_cost
0.013665
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
199
0.00%
Dialogue to Total Word Ratio
Ratio: 79.80%, Deviation: 29.80%
neededClean
false
wordsTotal
203
wordsDialogue
162
49.9995%