NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1GKD1X428M56STQSEQNG9P
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.4s
Cost:
$0.012865
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
93.47%
Dialogue to Total Word Ratio
(details)
96.6937%
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 kid's birthday party?" "Not a kid's party," Molly said. "A rich kid's party. Different thing entirely." "How's it different?" "The presents are nicer." "Molly, there'll be parents. Clowns. Witnesses under four feet tall." "Children can't testify. Everybody knows that." "That's not—where did you even hear that?" "Same place you heard we couldn't get caught last time." "We did get caught last time." "And yet here we are, free as birds. So my information's solid." Bill rubbed his temples. "What's the plan, then?" "You distract everyone. Balloon animals." "I can't make balloon animals." "Then make balloon shapes. Nobody's grading you." "And you?" "I sneak in, grab the gift table, and we vanish before they cut the cake." "You're skipping the cake?" "Bill, we're committing a felony. We're not staying for cake." "There's always time for cake." "Fine. We grab a slice on the way out. Happy?" "Ecstatic. What if a kid sees us?" "We say we're the entertainment." "Dressed in ski masks?" Molly paused. "Ninja-themed party. We commit to the bit." "This is the worst plan you've ever had." "Worse than the aquarium?" "...Marginally better than the aquarium." "Then we're golden. Grab your balloons."
created_at
"2026-06-01T11:55:11.81Z"
6/1/2026, 11:55:11 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1368
moderation_latency
184
generation_time
10181
tokens_prompt
77
tokens_completion
361
native_tokens_prompt
93
native_tokens_completion
496
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
0.012865
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_011nPZSZ5uXEJYDVdDxJyeQj"
is_byok
false
latency
1076
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-1780314911-f8PTJOd6IjpnWSHKNKGm"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780314911-C0CVGBbrOoZu7U8oJIX4"
upstream_id
"msg_011nPZSZ5uXEJYDVdDxJyeQj"
total_cost
0.012865
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
203
93.47%
Dialogue to Total Word Ratio
Ratio: 95.10%, Deviation: 5.10%
neededClean
false
wordsTotal
204
wordsDialogue
194
96.6937%