NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1HXN1KCXY7PXPHKXKF4HZN
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.7s
Cost:
$0.013940
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
78.17%
Dialogue to Total Word Ratio
(details)
89.0867%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"So we're really doing this?" Bill asked. "Robbing a six-year-old?" "Not robbing. Liberating," Molly said. "Those presents are practically begging to be stolen." "They're wrapped in unicorn paper, Molly." "Premium loot. Focus, Bill." "What's the plan?" "You're the entertainment. Bozo the Clown." "Absolutely not." "The costume's in the trunk." "I have dignity!" "You stole a kidney from a hospital last week." "That had dignity! Clowns are terrifying!" "Exactly. You'll distract the kids while I sweep the gift table." "And the parents?" "Cake. There's always cake. Parents swarm it like pigeons." "This is insane." "It's foolproof. What could a bunch of kindergartners possibly do?" "They bite, Molly. I've seen documentaries." "Wear the gloves." "And if someone recognizes us?" "From what? You'll be Bozo. I'll be the face-painting lady." "You can't paint faces!" "I'll paint something. A blob. They're children, Bill, their standards are low." "This feels morally questionable." "We robbed a children's hospital." "Stop bringing that up!" "Then commit. Honk the nose, juggle a little, and when I signal—" "What's the signal?" "I'll yell 'piñata.' Everyone goes berserk for piñatas." "And then?" "We grab the presents and run." Bill sighed. "I hate this job." "You said that about the orphanage too."
created_at
"2026-06-01T12:18:16.247Z"
6/1/2026, 12:18:16 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1135
moderation_latency
161
generation_time
10504
tokens_prompt
77
tokens_completion
383
native_tokens_prompt
93
native_tokens_completion
539
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
0.01394
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01BFXdg2BkQikVVG4tEf6v27"
is_byok
false
latency
1134
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-1780316296-1kLoZWQ5SeHxdHLbDQ6p"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316296-TkmcYzUX4LfipJ63Cfdy"
upstream_id
"msg_01BFXdg2BkQikVVG4tEf6v27"
total_cost
0.01394
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
200
78.17%
Dialogue to Total Word Ratio
Ratio: 97.04%, Deviation: 7.04%
neededClean
false
wordsTotal
203
wordsDialogue
197
89.0867%