NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSK0QJAHED0P3JX2A4W2BKQ
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.6s
Cost:
$0.012890
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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 blueprints across the table, knocking over a juice box. "Okay," she said, jabbing a finger at the diagram. "The party starts at two. We hit it during the piñata." Bill squinted. "Why the piñata?" "Because everyone's distracted, Bill. Blindfolds, swinging sticks, total chaos. Nobody's watching the gift table." "I don't know, Molly. These are kids' presents. Coloring books. Maybe a yo-yo." "It's a rich kid's party," she snapped. "Think tablets. Think gold-plated building blocks. Think bicycles, Bill." He scratched his chin. "What about the clown?" "What about him?" "Clowns are unpredictable. One time a clown chased me six blocks over a balloon animal." Molly stared at him. "That's your trauma talking. Focus. You distract the parents, I grab the loot, we're gone before the cake." "And if someone sees us?" "We're wearing party hats. We blend in." Bill brightened. "I do look fantastic in a party hat." "That's the spirit." She rolled up the blueprints. "Any questions?" "Just one." He leaned forward seriously. "Can I have a slice of cake before we leave?" Molly closed her eyes and exhaled slowly. "Fine. One slice." "And a goodie bag?" "Don't push it, Bill." He grinned, clutching his tiny party hat like a crown.
created_at
"2026-05-29T10:03:30.262Z"
5/29/2026, 10:03:30 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
964
moderation_latency
(null)
generation_time
9577
tokens_prompt
77
tokens_completion
345
native_tokens_prompt
93
native_tokens_completion
497
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
0.01289
router
(null)
provider_responses
0
endpoint_id
"dfc0e5bd-d703-4fe2-a7bb-655eb95d5441"
id
"msg_01CcKLRZYwxWK1QpTrDHHcrf"
is_byok
false
latency
964
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-1780049010-6jSbJ3OcJMdTzCwfLtJ1"
session_id
(null)
api_type
"completions"
id
"gen-1780049010-XMBuZwMyu9sRTXh9iMd2"
upstream_id
"msg_01CcKLRZYwxWK1QpTrDHHcrf"
total_cost
0.01289
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
0.00%
Dialogue to Total Word Ratio
Ratio: 70.87%, Deviation: 20.87%
neededClean
false
wordsTotal
206
wordsDialogue
146
49.8722%