NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXDA7EWHSS9VZAYMQP396Y
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
20.2s
Cost:
$0.048625
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The rain hammered against the old mansion windows as Detective Sarah Cole stepped slowly across the creaking wooden floor inside. A single candle flickered upon the marble table where the body of Lord Harrington lay perfectly still and quite cold. His glassy eyes stared toward the ceiling while crimson blood pooled around the silver dagger buried deep within his chest. Detective Cole knelt beside him, her trained eyes scanning every detail of the gruesome scene before quietly drawing her breath. Outside the storm raged louder, yet inside the silence felt heavier than any sound she had ever truly experienced before. Five guests remained trapped within these walls tonight, and one among them had clearly committed this cold, calculated brutal murder. She rose to her feet, turning toward the frightened faces gathered nervously in the doorway of the dimly lit room. Nobody moved, nobody spoke, and every single person there understood the long, terrible night had only just begun for them.
created_at
"2026-05-31T11:41:20.509Z"
5/31/2026, 11:41:20 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3589
moderation_latency
(null)
generation_time
20155
tokens_prompt
46
tokens_completion
395
native_tokens_prompt
60
native_tokens_completion
1933
native_tokens_completion_images
(null)
native_tokens_reasoning
133
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
0.048625
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01HG87z8Nu5DhohtfwriJktB"
is_byok
false
latency
1070
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-1780227680-nbliJqTvTyPaSKXLkiPo"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227680-qdpo5a0VgIrMVCVLjnPY"
upstream_id
"msg_01HG87z8Nu5DhohtfwriJktB"
total_cost
0.048625
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
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20