NC Bench
Overview
About
Tests
Models
Model
Liquid: LFM 40B MoE
Test
N-Length Sentences
Scenario
Write sentences with 5 words each
Run ID
2024-10-01-01J94R8F2D83DP1E17KG4PVEM2
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 5 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Jaaa: aaaaat; sassss: attic door sllllid; open. Scene set | Find a fedora. Sacrament; evidence plan laced with Martini shards T: Tormented figures circle j. UNABLE LO: Kit IN Scream; intrinsic silence slides prison shadowroom with candlelight souls. Sparks; victims raining jailed sky beating guttural chorale refrains bloody ignites Wells. Dozen; police methods decor dim circle waiting grin victims bone moldings aeons conquered shattered doors lock Coals. Candlestick seems DOS say!!! innocent...Leave little red body organs check crime cooled spine freezer ashy yellow shadow EXPLOSIONS screeching hands fisticromping treacherous traps tremble juggle do now WHAT food blueblast BLOODSCATTERED mudkit piles vile innocences LEAVE hallways stonewalls FUNNELING into FOODYELLOW fuming RPMs kissing Jewelry breast then GREATAWAY is STAIRWAY lonely its bones ticking drop wicked ill man Carrie-BEEN. PUPILS uranium diner coffee knees shaken wince wondered silenced matters murmuring rustling microphones popping tipped.
id
"gen-1727810256-gdOVcYwwc5nNgRP0EQ2Y"
total_cost
0
upstream_id
"chatcmpl-082a86af-08c2-45b3-9aee-19933a1955d3"
created_at
"2024-10-01T19:17:37.864935+00:00"
Tuesday, October 1st, 2024 at 7:17:37 PM GMT+00:00
model
"liquid/lfm-40b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Lambda"
latency
178
moderation_latency
(null)
generation_time
1340
finish_reason
"stop"
tokens_prompt
69
tokens_completion
238
native_tokens_prompt
102
native_tokens_completion
300
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0
Evaluation details
Result
Evaluator
Details
Meta Data
17.5102%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
7
1
6
2
12
3
13
4
12
5
17
6
4
7
56
8
15