NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJZMN4TGNNDWGAR7V3D1FM
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.2s
Cost:
$0.014890
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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 crayon-drawn map across the table, smoothing its glittery edges. "The party starts at noon," she said, tapping a sticker. "Bouncy castle here, clown there, and the present table is the soft underbelly." Bill squinted through his binoculars at the suburban house. "There's a six-year-old guarding the gifts. Looks vicious." "That's the birthday girl, Bill." "She's wearing a tiara. Royalty's always trouble." Molly sighed and snatched the binoculars away. "Focus. We go in disguised as entertainers. You're the magician, I'm the face-painter." "I don't know any magic." "Neither do real magicians. You wave, you mumble, you palm a present." Bill chewed his thumbnail nervously. "What about the parents?" "Distracted by juice boxes and existential dread. Trust me, nobody watches the loot once the piƱata swings." "And the dog?" "There's a dog?" "Big one. Named Sprinkles, apparently." Molly considered this, then pulled out a sandwich bag of sausages. "Sprinkles gets bribed. Everyone gets bribed at these things." Bill grinned, finally relaxing. "I love an inside job." "It's a children's party, not a bank." "Same adrenaline," he insisted, fluffing his cape. "Now, do these spandex tights make me look like I steal candy?" "Yes," Molly said. "Perfect."
created_at
"2026-05-29T10:02:54.509Z"
5/29/2026, 10:02:54 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2733
moderation_latency
(null)
generation_time
11121
tokens_prompt
77
tokens_completion
394
native_tokens_prompt
93
native_tokens_completion
577
native_tokens_completion_images
(null)
native_tokens_reasoning
46
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
0.01489
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01VAEMxEVSYmYq4aZ7s2R4qB"
is_byok
false
latency
1112
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-1780048974-RjtrJBx0wTmCtpyzY5HJ"
session_id
(null)
api_type
"completions"
id
"gen-1780048974-E5FDuC1LbGjGJX4RMQrP"
upstream_id
"msg_01VAEMxEVSYmYq4aZ7s2R4qB"
total_cost
0.01489
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 69.65%, Deviation: 19.65%
neededClean
false
wordsTotal
201
wordsDialogue
140
49.9595%