NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1J2VJX953YCSN4357JMP9T
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.6s
Cost:
$0.014115
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
95.19%
Dialogue to Total Word Ratio
(details)
97.4680%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crouched behind the hedge, binoculars trained on the bouncy castle as if it were a maximum-security vault. Beside her, Bill unfolded a hand-drawn map labeled "Operation Cupcake," complete with stick figures and an alarming number of frosting stains. He had spent forty minutes on it and was, frankly, proud. The target was a sixth birthday party for a child named Timothy, whose parents had committed the grievous error of posting the gift table online. Forty-seven wrapped presents glittered in the afternoon sun, guarded only by a clown named Mr. Sprinkles and a folding table groaning under its load. "We go in through the piñata," Bill whispered. Molly stared at him. The piñata was a paper donkey suspended from an oak branch. It was not, by any reasonable metric, an entry point. She returned to surveilling the perimeter, noting the buffet of juice boxes, the territorial grandmother, and the dog wearing a party hat. Their plan, such as it was, hinged on disguising themselves as entertainers. Molly had a balloon-animal kit. Bill had a tuba, for reasons he refused to explain. Together they looked less like criminals and more like a circus that had been fired. "This is foolproof," he insisted. It was not.
created_at
"2026-06-01T12:21:06.786Z"
6/1/2026, 12:21:06 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3423
moderation_latency
(null)
generation_time
9615
tokens_prompt
77
tokens_completion
383
native_tokens_prompt
93
native_tokens_completion
546
native_tokens_completion_images
(null)
native_tokens_reasoning
65
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
0.014115
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01Ez26U7rjs9CmcbQuCVzBuR"
is_byok
false
latency
1074
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-1780316466-2Ob0qbHgovU3CUpc8Q3V"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316466-BmYgGZN0lS32VY5nbaAV"
upstream_id
"msg_01Ez26U7rjs9CmcbQuCVzBuR"
total_cost
0.014115
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
95.19%
Dialogue to Total Word Ratio
Ratio: 5.29%, Deviation: 4.71%
neededClean
false
wordsTotal
208
wordsDialogue
11
97.4680%