NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1H0FX3DTFDJ267YBSYZHQP
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.8s
Cost:
$0.012140
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9998%
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 blueprint across the table, smoothing out a crumpled corner shaped suspiciously like a juice box stain. "The bounce house is our blind spot," she said. "Nobody watches the perimeter when there's a bounce house." Bill squinted at the diagram. "What's this circle here?" "That's the piñata. We avoid the piñata." "Why?" "Because, Bill, when that thing breaks, it's chaos. Children everywhere. Candy raining down. You do not want to be standing under a piñata when forty kids lose their minds." He nodded slowly, absorbing this wisdom. "And the presents?" "Stacked by the cake table. We grab the gift bags first—lightweight, high value. Then the big boxes." "What about the parents?" "Distracted," Molly said confidently. "There's always one dad filming everything and one mom crying about how fast they grow up. Neither of them sees a thing." Bill scratched his chin. "And the clown?" "What clown?" "There's always a clown." Molly froze. She hadn't considered the clown. The clown was a wildcard, an agent of unpredictable mayhem. "Okay," she admitted quietly. "The clown could be a problem." "Told you." "We bring balloons," she decided. "We blend in. We become the entertainment." Bill grinned. "I've always wanted to juggle."
created_at
"2026-06-01T12:02:20.714Z"
6/1/2026, 12:02:20 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1077
moderation_latency
(null)
generation_time
8750
tokens_prompt
77
tokens_completion
344
native_tokens_prompt
93
native_tokens_completion
467
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
0.01214
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01Bt2BknX31kizaUoixKVTaT"
is_byok
false
latency
1077
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-1780315340-TUaqK9yhkhTbaJOGgKtn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315340-7tA8fZnk8qGe1reeMU6v"
upstream_id
"msg_01Bt2BknX31kizaUoixKVTaT"
total_cost
0.01214
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
201
0.00%
Dialogue to Total Word Ratio
Ratio: 68.66%, Deviation: 18.66%
neededClean
false
wordsTotal
201
wordsDialogue
138
49.9998%