NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ01E232M4DVBXASH5K2EXAQ
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 36s
Cost:
$0.032199
Provider:
Friendli
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
66.39%
Dialogue to Total Word Ratio
(details)
83.1958%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Are we really doing this?" Bill whispered. "It's a total goldmine," Molly replied. "It's a little kid's birthday party." "Exactly. Zero security, low threat level, massive yield." "They're children!" "Children who get spoiled with extremely expensive electronics. Do you know what a modern console goes for on the secondary market?" "We still have to get past the bouncy castle." "I've got the aerial entry mapped out. You hit the snack table, create a loud diversion." "What kind of diversion?" "Just knock over the juice boxes. When the moms rush for paper towels, I repel down from the ceiling fan." "Rappelling? In a suburban living room?" "It's a tactical insertion. Grab the wrapped presents, stuff them in the loot sack, and we vanish before the clown finishes his balloon animal routine." "What if the clown fights back?" "Clowns are strictly civilians. Besides, I have the tactical pepper spray." "What if a kid starts crying?" "You grab the Lego set, I'll grab the designer doll, and we meet at the getaway van. Stop overthinking the collateral damage." "I just never thought I'd have to suplex a toddler for a Barbie Dreamhouse." "Desperate times, Billy. Now zip up your ninja turtle ski mask."
created_at
"2026-04-24T15:23:48.205Z"
4/24/2026, 3:23:48 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5261
moderation_latency
(null)
generation_time
95449
tokens_prompt
77
tokens_completion
6021
native_tokens_prompt
66
native_tokens_completion
7297
native_tokens_completion_images
(null)
native_tokens_reasoning
5706
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
"stop"
usage
0.0321992
router
(null)
provider_responses
0
endpoint_id
"d4443f1c-fdb1-4cf0-a381-5b77b7e25ae7"
id
"chatcmpl-7e96be2ca93c4dd0a967a19306c62476"
is_byok
false
latency
5261
model_permaslug
"z-ai/glm-5.1-20260406"
provider_name
"Friendli"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777044228-oUl8okYFcpmPcuHRZB6g"
session_id
(null)
api_type
"completions"
id
"gen-1777044228-qBH0NQ7Np1TT2xPxpmr0"
upstream_id
"chatcmpl-7e96be2ca93c4dd0a967a19306c62476"
total_cost
0.0321992
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Friendli"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
66.39%
Dialogue to Total Word Ratio
Ratio: 98.00%, Deviation: 8.00%
neededClean
false
wordsTotal
200
wordsDialogue
196
83.1958%