NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSKD625H1MAQMVZXB1Q22HQ
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.7s
Cost:
$0.012040
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
65.21%
Dialogue to Total Word Ratio
(details)
79.4309%
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 said. "We're really doing this," Molly confirmed. "Robbing a child." "Robbing *multiple* children, technically." "Right. The classy option." "Look, do you want to eat this month or not?" "I want to keep my dignity." "Your dignity bounced a check last Tuesday, Bill." "That's fair. So what's the plan?" "You go in dressed as the clown. I come in as the magician." "Why do you get magician? Magicians are cool." "Because you have a face people instinctively trust on a clown." "That's the meanest compliment I've ever received." "Take it. Now, the presents are stacked by the gift table. You distract the kids with balloon animals—" "I don't know how to make balloon animals." "Then make balloon *blobs*. Kids are stupid, they'll love it." "And what do you do?" "I 'magically' make the presents disappear into a duffel bag." "That's not magic, that's just theft with extra steps." "All magic is theft with extra steps, Bill." "That's weirdly profound." "I read a book once." "What if a parent catches us?" "Then you honk your little horn and we run." "I don't have a little horn." "Buy a little horn, Bill." "Fine. But I want it noted I have concerns." "Noted. Now grab the balloons."
created_at
"2026-05-29T10:10:18.32Z"
5/29/2026, 10:10:18 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3080
moderation_latency
(null)
generation_time
11623
tokens_prompt
77
tokens_completion
353
native_tokens_prompt
93
native_tokens_completion
463
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
0.01204
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01DtJL76i16RNpb3HYj4FDJ7"
is_byok
false
latency
3080
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-1780049418-FY7j2MRos6KM6wXApfHw"
session_id
(null)
api_type
"completions"
id
"gen-1780049418-PJ1sFkuReiaoyGqRLtXW"
upstream_id
"msg_01DtJL76i16RNpb3HYj4FDJ7"
total_cost
0.01204
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
65.21%
Dialogue to Total Word Ratio
Ratio: 98.09%, Deviation: 8.09%
neededClean
false
wordsTotal
209
wordsDialogue
205
79.4309%