NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSK6AEYXYND1M42M5942EK7
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.0s
Cost:
$0.014865
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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 it with the reverence of a general. "The bouncy castle is our blind spot," she said. "Nobody watches the bouncy castle." Bill squinted at the diagram. "And the presents?" "Pile by the cake table. Forty, maybe fifty gift bags. We're talking premium loot—action figures, art kits, those squishy stress balls that go for a fortune resale." "I'm allergic to clowns," Bill admitted, fidgeting. "There's a clown?" "There's always a clown, Molly. They're security in disguise." She rolled her eyes and tapped the map. "You'll create a distraction. Pretend you lost a balloon animal. While they're consoling you, I sweep the table." "What if a child notices?" "Children are unreliable witnesses," she said briskly. "They'll blame the dog." "There's a dog?" "There's always a dog, Bill." He swallowed hard. "And the getaway?" "Out through the garden, over the fence, into the ice cream van." "We have an ice cream van?" "I rented one. Nobody suspects an ice cream van." Bill nodded slowly, then frowned. "This feels deeply wrong." "It's a heist," Molly said, folding the map. "It's supposed to feel wrong. Now grab the ski masks and the juice boxes."
created_at
"2026-05-29T10:06:33.615Z"
5/29/2026, 10:06:33 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3898
moderation_latency
(null)
generation_time
10720
tokens_prompt
77
tokens_completion
384
native_tokens_prompt
93
native_tokens_completion
576
native_tokens_completion_images
(null)
native_tokens_reasoning
52
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
0.014865
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01UDwnQH9rT717hShnVurK49"
is_byok
false
latency
1138
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-1780049193-Fo4LNq5Ssnzx5Aj2vxPW"
session_id
(null)
api_type
"completions"
id
"gen-1780049193-tCCRnCKShlfAvfVn9S9i"
upstream_id
"msg_01UDwnQH9rT717hShnVurK49"
total_cost
0.014865
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
199
0.00%
Dialogue to Total Word Ratio
Ratio: 74.50%, Deviation: 24.50%
neededClean
false
wordsTotal
200
wordsDialogue
149
49.9995%