NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ06FD9GP28SHKYNK2F4TTPM
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 1s
Cost:
$0.035099
Provider:
Friendli
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly adjusted her binoculars, the neon bounce house reflecting sharply in the lenses. Beside her, Bill munched on stolen candyfloss, looking thoroughly unconvinced by their current surveillance. The target was a wealthy toddler birthday bash, overflowing with expensive designer toys. A golden tricycle sat enticingly near the gift table. It was a dangerous job, assuming you considered face painting and toddler screaming as serious occupational hazards. The venue security was remarkably minimal, just a tired clown making balloon animals near the gate. They had the blueprints, the timeline, and a very large sack. It was time to execute the plunge. "Are you absolutely sure we can outrun a vicious mob of sugared six year olds?" "They have tiny legs, Bill. We clearly have the tactical advantage." "But what if the clown has a real weapon hidden?" "It is a balloon sword. You parry, I grab the wrapped presents." "What if they start crying very loudly?" "They are already crying. It is a kid party. Grab the shiny boxes and run for the van." "Fine, but if that clown comes at me, I am tackling him to the ground." "Just focus on the loot, keep your shoes clean, and avoid frosting."
created_at
"2026-04-24T16:51:55.322Z"
4/24/2026, 4:51:55 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
332
moderation_latency
(null)
generation_time
60855
tokens_prompt
77
tokens_completion
6344
native_tokens_prompt
66
native_tokens_completion
7956
native_tokens_completion_images
(null)
native_tokens_reasoning
6040
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
0.0350988
router
(null)
provider_responses
0
endpoint_id
"d4443f1c-fdb1-4cf0-a381-5b77b7e25ae7"
id
"chatcmpl-12493b3a28a045498aa2a0b741ee6577"
is_byok
false
latency
332
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-1777049515-q6dUCeWJutToRHDlQ3nm"
session_id
(null)
api_type
"completions"
id
"gen-1777049515-ilTVEiZqkaEMiOlfwMgk"
upstream_id
"chatcmpl-12493b3a28a045498aa2a0b741ee6577"
total_cost
0.0350988
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
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%