NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ06JE3SDEMWXKY13TB2BCHM
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 42s
Cost:
$0.023351
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
95.89%
Dialogue to Total Word Ratio
(details)
97.9429%
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
"So we go in through the bouncy castle," Molly said, adjusting her black turtleneck. "Inflatable entry. Classic. What about the clown?" Bill asked, checking his earpiece. "I'll handle the clown. You grab the loot." "What if the kids get suspicious?" "They're six. Just tell them we're the present inspectors." "Present inspectors? That's ridiculous." "Works every time. Now, the target is the mountain of gifts by the pinata." "Pinata? What if it breaks while we're inside?" "Then you hit the deck. Blindfolded kids with bats are a liability, Bill." "Maybe I wear a helmet." "You're stealing from toddlers, Bill. Have some dignity. Grab the shiny packages, avoid the ones that rattle, and meet me by the ice cream truck." "Why avoid the rattlers?" "Legos. Stepping on a Lego during a getaway is a rookie mistake. I lost a toe in eighty-nine." "Right. Safety first. What's the exit strategy?" "Slip and slide out the backyard." "I always ruin my pants on those things." "Wear synthetics. Move fast, grab big, and whatever you do, do not make eye contact with the birthday boy." "What if he cries?" "Then we run. No hesitating. I won't go back to the ball pit. Not ever again."
created_at
"2026-04-24T16:53:34.467Z"
4/24/2026, 4:53:34 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2013
moderation_latency
(null)
generation_time
101997
tokens_prompt
77
tokens_completion
4556
native_tokens_prompt
66
native_tokens_completion
5286
native_tokens_completion_images
(null)
native_tokens_reasoning
5001
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
0.0233508
router
(null)
provider_responses
0
endpoint_id
"0ef82a37-906f-4cbe-99fc-3645b17597ff"
id
"019dc069399d5629e109d05d525ff85f"
is_byok
false
latency
2010
model_permaslug
"z-ai/glm-5.1-20260406"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777049614-vSIhqjEBonvo23uPfrtg"
session_id
(null)
api_type
"completions"
id
"gen-1777049614-FXADhUg6Ze0Y03sEguI2"
upstream_id
"019dc069399d5629e109d05d525ff85f"
total_cost
0.0233508
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
95.89%
Dialogue to Total Word Ratio
Ratio: 94.53%, Deviation: 4.53%
neededClean
false
wordsTotal
201
wordsDialogue
190
97.9429%