NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1HH4QKG9HXBEVHB9PZWTYH
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.2s
Cost:
$0.014415
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
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 crayon-stained paper with trembling hands. "Right," she said. "The bouncy castle is our weak point. Security's distracted, sugar's flowing, nobody's watching the gift table." Bill squinted at the diagram. "Why is there a clown drawn in the corner?" "That's not a clown, Bill. That's the threat assessment. Reginald the Magnificent does balloon animals at three o'clock sharp." "And we hit the presents during the balloon animals?" "We hit the presents," she confirmed, "during the balloon animals." He chewed his thumbnail nervously. "I don't love this. Last time we robbed a birthday party, I got cake in my mustache and a four-year-old bit my ankle." "That four-year-old," Molly said gravely, "is now their head of operations. We respect the threat." "What's the extraction plan?" "We wheel the loot out in the piƱata. Big paper donkey, nobody questions it." Bill brightened considerably. "Genius. And if anyone stops us?" "You're the magician's assistant. I'm the caterer. We improvise." "I can't do magic, Molly." She zipped up her ski mask and grinned. "Neither can Reginald, mate. That's why we'll fit right in. Now grab the donkey and let's go ruin a child's afternoon."
created_at
"2026-06-01T12:11:26.329Z"
6/1/2026, 12:11:26 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2886
moderation_latency
(null)
generation_time
9999
tokens_prompt
77
tokens_completion
388
native_tokens_prompt
93
native_tokens_completion
558
native_tokens_completion_images
(null)
native_tokens_reasoning
49
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
0.014415
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_013zZNrxUsin8pyuFptJzdJH"
is_byok
false
latency
1183
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-1780315886-Ren7W1EvZaKWXknyQWYN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315886-zLiuHUAbxOKGQr6hp8aG"
upstream_id
"msg_013zZNrxUsin8pyuFptJzdJH"
total_cost
0.014415
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
202
0.00%
Dialogue to Total Word Ratio
Ratio: 77.29%, Deviation: 27.29%
neededClean
false
wordsTotal
207
wordsDialogue
160
49.9920%