NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YCN3KN7T4B1HP1ZRXBYDB
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.6s
Cost:
$0.000111
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0004%
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 tactical glitter headband. "The target is the bouncy castle, Bill. High visibility, low security." Bill squinted at his blueprint, which was actually a coloring book page. "Is the clown a mercenary or a civilian?" "He is a distraction," Molly whispered, checking her lockpicks. "Once the cake is cut, we strike the gift pile." "What about the sugar rush?" Bill asked, sweating. "The toddlers will be feral." "We use the smoke grenades. Pink ones. To blend with the confetti." "And the loot?" Bill gripped his empty sack. "Is it high-end electronics?" "Better," Molly grinned. "Lego sets. Limited editions. Pure plastic gold." "I feel a moral conflict," Bill muttered. "They are only five." "Morality doesn't pay for my yacht, Bill. Now, grab the frosting-smudged binoculars." "Do I have to wear the propeller hat?" Bill sighed. "It is part of the disguise. Keep it steady." "This is the most humiliating heist of my career," Bill complained. "Quiet! The birthday boy is blowing out the candles. Move in!"
created_at
"2026-05-10T12:39:28.122Z"
5/10/2026, 12:39:28 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1258
moderation_latency
(null)
generation_time
5317
tokens_prompt
77
tokens_completion
277
native_tokens_prompt
79
native_tokens_completion
255
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
service_tier
(null)
usage
0.00011148
router
(null)
provider_responses
0
endpoint_id
"2e9daaa4-87bf-49f7-a44a-2c1d617c2c51"
is_byok
false
latency
104
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Venice"
status
429
1
endpoint_id
"eb382d64-dce1-42d5-b23d-6fefb91948a3"
id
"chatcmpl-8c5b3cdb9d2d1440"
is_byok
false
latency
1258
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778416768-EefWn5Vg1q0Lz22wJO0I"
session_id
(null)
api_type
"completions"
id
"gen-1778416768-dFWbt1f6XPoqjIkBemF4"
upstream_id
"chatcmpl-8c5b3cdb9d2d1440"
total_cost
0.00011148
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
167
0.00%
Dialogue to Total Word Ratio
Ratio: 76.92%, Deviation: 26.92%
neededClean
false
wordsTotal
169
wordsDialogue
130
0.0004%