NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXPV6BP25BWXSD2GT56HS5
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
33.8s
Cost:
$0.090975
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 fell hard against the old manor windows as Detective Sarah Hayes stepped carefully across the dusty threshold inside. A single dim chandelier flickered overhead, casting long shadows that danced nervously along the cracked walls and cold marble floor. There, sprawled beneath the grand staircase, lay the body of the wealthy old patriarch Edward Crowley, his eyes wide open. Blood pooled darkly across the white marble, spreading slowly toward the fallen silver candlestick lying near his cold outstretched hand. Sarah knelt down, her gloved fingers hovering just above the open wound, knowing immediately this meant deliberate, cold, calculated murder. Behind her, the assembled houseguests gathered silently in the doorway, their pale faces frozen between genuine shock and quiet guilt. Someone in this very room had murdered Edward Crowley tonight, and Sarah intended to discover exactly who before sunrise came.
created_at
"2026-05-31T11:46:32.791Z"
5/31/2026, 11:46:32 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4087
moderation_latency
(null)
generation_time
33794
tokens_prompt
46
tokens_completion
513
native_tokens_prompt
60
native_tokens_completion
3627
native_tokens_completion_images
(null)
native_tokens_reasoning
271
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
0.090975
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01J6ndPAEAkeh9XT2pTux6Ht"
is_byok
false
latency
1426
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-1780227992-Bcq9ySx0BDJCYl5Otg3l"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227992-VTTuYV3OjId8AUG41e2R"
upstream_id
"msg_01J6ndPAEAkeh9XT2pTux6Ht"
total_cost
0.090975
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
7
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20