NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYYQ3CZVVFGH4K25XTRG0Y8
Run Details
Model:
Z.AI GLM 4.7 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
27.5s
Cost:
$0.000859
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
60.67%
Dialogue to Total Word Ratio
(details)
80.2933%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 ski mask and checked the tactical flashlight against her badge of authenticity. Bill was crouched before the piñata, inspecting the structural weakness with the scrutiny of a bomb disposal expert. It was a unicorn. A terrible, latex-filled target. "Too soft," Bill muttered, tapping the plastic horn. They waited behind the overgrown hedge, listening to the shrieks of third graders inside. The loot was locked in the garage, protected by the golden child of the decade. This was a fortress. Molly pulled a modified grappling hook from her utility belt, shaped like a glow-in-the-dark lizard. "If we get caught," she whispered, "the witness protection program is already waiting in Prague." Bill nodded, eyeing the back door. "Good thing we brought the incendiary device." It was merely a bag of fireworks intended for the big kid’s surprise. "Operation Unicorn Derailment commencing." They crept through the blooming azaleas, weapons drawn. The air smelled of cupcakes and desperation. The target was secure. Molly checked her watch. "Laser grid?" "Already cut," Bill said, tossing a pristine slice of construction paper into the air. "Zero clearance." Molly smirked behind her mask, admiring the logistical masterpiece. "Alright then. To the loot."
created_at
"2026-02-08T15:43:21.503723+00:00"
2/8/2026, 3:43:21 PM
model
"z-ai/glm-4.7-flash-20260119"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1420
moderation_latency
(null)
generation_time
27099
tokens_prompt
61
tokens_completion
2120
native_tokens_prompt
66
native_tokens_completion
2142
native_tokens_completion_images
(null)
native_tokens_reasoning
2042
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
0.0008591600000064
router
(null)
provider_responses
0
id
"chatcmpl-RT4mDHmMFhqVV1GtS7jPk2OU"
status
200
is_byok
false
latency
60
endpoint_id
"6efb5994-8fcb-4300-9c64-ba393193f5f6"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.7-flash-20260119"
api_type
"completions"
id
"gen-1770565373-UqLtGjrSpVBVGWGEQ0o9"
upstream_id
"chatcmpl-RT4mDHmMFhqVV1GtS7jPk2OU"
total_cost
0.0008591600000064
cache_discount
0.0000015999999936
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
60.67%
Dialogue to Total Word Ratio
Ratio: 18.41%, Deviation: 8.41%
neededClean
false
wordsTotal
201
wordsDialogue
37
80.2933%