NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ03QFE6S13A3K13QXZJ482M
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 31s
Cost:
$0.038324
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
65.99%
Dialogue to Total Word Ratio
(details)
82.9943%
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 the target is 427 Maple Drive," Molly said. "The compound?" Bill asked. "The bouncy castle, Bill. Keep up." "Right, right. What's the entry point again?" "The side gate. It's a princess party, so security is a guy in a foam dragon costume." "Do I take him out quietly?" "Just bribe him with apple juice boxes. Now, the safe is the gift table." "Where's the vault?" "Right under the banner that says Happy Birthday Timmy. We go in during the cake cutting. The candles blow out, lights go dark, we grab the loot, and we're out before the clown makes a balloon dog." "What's the loot?" "Lego sets, Bill. Mint condition. We're talking Star Wars Ultimate Collector Series, still in the shrink wrap. A Millennium Falcon on the black market pays for our winter in Bali." "We're really stealing Legos from a seven-year-old kid?" "We're liquidating high-yield plastic assets. You got a problem with that?" "No, but what if he cries?" "That's what the lollipop is for. Distraction and pacification. Now put on the clown nose." "It's way too small. It's cutting off the circulation to my face." "Suck it up, Bill. The party starts in five minutes. Let's go."
created_at
"2026-04-24T16:03:53.936Z"
4/24/2026, 4:03:53 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
453
moderation_latency
(null)
generation_time
91038
tokens_prompt
77
tokens_completion
7148
native_tokens_prompt
66
native_tokens_completion
8689
native_tokens_completion_images
(null)
native_tokens_reasoning
6848
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
0.038324
router
(null)
provider_responses
0
endpoint_id
"0a3f7e48-cd4f-4fcf-88dd-3ab61bb5e7d1"
id
"ogSXVwm-2byqsH-9f165736349c392b"
is_byok
false
latency
453
model_permaslug
"z-ai/glm-5.1-20260406"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777046633-uCNFtCNmO9n11sT09QSK"
session_id
(null)
api_type
"completions"
id
"gen-1777046633-hbLXmaVxcpmT8aRal6fX"
upstream_id
"ogSXVwm-2byqsH-9f165736349c392b"
total_cost
0.038324
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
65.99%
Dialogue to Total Word Ratio
Ratio: 98.03%, Deviation: 8.03%
neededClean
false
wordsTotal
203
wordsDialogue
199
82.9943%