NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40D71XAFWD02ZB7TXP69WW
Run Details
Model:
GPT-5.6 Terra (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
10.3s
Cost:
$0.016033
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.08%
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
Rain hammered Blackthorn Hall as Inspector Mara Venn arrived, finding the front door open and servants whispering fearfully inside. Lord Ashcombe lay beneath the library window, a silver letter opener buried neatly between his astonished shoulder blades at dawn. Beside him, a stopped clock showed eleven seventeen, while muddy footprints crossed the Persian rug toward the locked study door. Mara noted the footprints ended abruptly, as though their owner had vanished through the paneling without disturbing any dust nearby. The housekeeper, Mrs. Pike, clutched a candle and claimed everyone had remained downstairs during the thunderstorm, except the victim himself. Then the dead man's pocket watch chimed once, although its hands were frozen, and every witness turned toward Mara silently. Inside its cracked case, she found a tiny key, warm to the touch, and a name scratched carefully beneath it. It read, “Eleanor,” and upstairs, behind the study door, someone began playing the victim's favorite funeral march on piano softly.
created_at
"2026-07-09T17:57:00.622Z"
7/9/2026, 5:57:00 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7657
moderation_latency
(null)
generation_time
9956
tokens_prompt
46
tokens_completion
273
native_tokens_prompt
41
native_tokens_completion
1062
native_tokens_completion_images
0
native_tokens_reasoning
854
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
"completed"
service_tier
"default"
usage
0.0160325
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_074d0f424d2ccd90016a4fe0ecb1e8819490d2524ba135159c"
is_byok
false
latency
194
model_permaslug
"openai/gpt-5.6-terra-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783619820-tdhW2XnMatFbmxBQlaPv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783619820-BA92WPrTfE0oAkBIPIda"
upstream_id
"resp_074d0f424d2ccd90016a4fe0ecb1e8819490d2524ba135159c"
total_cost
0.0160325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
95.08%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
19
1
20
2
20
3
20
4
20
5
20
6
20
7
20