NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2026-02-08-01KGYX00FWGEVGWWP7NWC2GB1T
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 slapped the “blueprints”—a crayon-scrawled map of a suburban backyard—onto the van’s greasy dashboard. The air inside smelled faintly of stale donuts and desperation. She tapped a franticly-drawn scribble labeled “Gift Table,” surrounded by smiling suns and what looked like a dinosaur. Across from her, Bill, a lanky man in an ill-fitting black turtleneck, was trying to stick a fake mustache over his own, which was significantly larger. The mission was absurd, but the rent was due. “Focus, Bill,” Molly snapped. “The objective is the presents, not the punch bowl.” “But the plan mentions a piñata,” he whined, the mustache now clinging to his cheek. “That’s a high-value target.” “It’s full of cheap Tootsie Rolls, not bearer bonds. Entry point is the side gate during the ‘pin the tail on the donkey’ phase. The clown provides cover.” “A clown? They’re unpredictable. What about the primary security? The giant inflatable castle? That’s a pressure-plate minefield.” “We circumvent the bouncy castle. You’re on distraction. If a child spots you, offer them a balloon. You’re ‘Uncle Barry.’” “Do I get a cool hat?” Bill asked, his eyes gleaming with misguided hope.
created_at
"2026-02-08T15:15:38.812414+00:00"
Sunday, February 8th, 2026 at 3:15:38 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
407
moderation_latency
(null)
generation_time
170367
tokens_prompt
61
tokens_completion
3828
native_tokens_prompt
66
native_tokens_completion
3871
native_tokens_completion_images
(null)
native_tokens_reasoning
3628
native_tokens_cached
32
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0067527199999776
router
(null)
provider_responses
0
id
"chatcmpl-RtsBbZTECsfInEsFJWQqyfbU"
status
200
is_byok
false
latency
73
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770563568-LJ82DvsLypa5mvT8xet2"
upstream_id
"chatcmpl-RtsBbZTECsfInEsFJWQqyfbU"
total_cost
0.0067527199999776
cache_discount
0.0000112000000224
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
194
86.3819%
Dialogue to Total Word Ratio
Ratio: 56.19%, Deviation: 6.19%
neededClean
false
wordsTotal
194
wordsDialogue
109
92.5471%