NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR92BCBKFAGJZKFHBYKHD4FT
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.8s
Cost:
$0.000106
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
99.52%
Dialogue to Total Word Ratio
(details)
79.8984%
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
The blueprints for the Henderson residence were spread across the grease-stained kitchen table, looking less like a criminal masterplan and more like a spilled bowl of spaghetti. Molly squinted through her tactical goggles, tapping a heavy finger on the diagram of the living room. It was a high-stakes battlefield of balloon animals and discarded juice boxes. The objective was clear: the mountain of brightly wrapped boxes sitting beneath the frosted pine tree. Bill adjusted his balaclava, which was currently snagged on his earring. He stared at the obstacle course of glitter-covered streamers blocking the main hallway. "Is that a laser security system?" Bill whispered, pointing at a string of colorful fairy lights. "No, it is just cheap decor," Molly hissed back. The perimeter was crawling with unpredictable elements. There were high-frequency shrieks capable of shattering glass and a biological hazard in the form of a sticky toddler wandering the halls. They needed precision, silence, and most importantly, a way to bypass the watchful eye of a golden retriever named Barnaby. "We grab the Lego sets first," Molly commanded. "And the remote-controlled cars?" Bill asked. "Naturally."
created_at
"2026-05-10T13:48:40.721Z"
5/10/2026, 1:48:40 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1129
moderation_latency
(null)
generation_time
3416
tokens_prompt
77
tokens_completion
312
native_tokens_prompt
79
native_tokens_completion
242
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
0.00010628
router
(null)
provider_responses
0
endpoint_id
"d99bcbe6-bec3-4991-965e-45fea79fe63c"
is_byok
false
latency
10077
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DekaLLM"
status
504
1
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
is_byok
false
latency
53
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DeepInfra"
status
429
2
endpoint_id
"eb382d64-dce1-42d5-b23d-6fefb91948a3"
id
"chatcmpl-81896370805aa30c"
is_byok
false
latency
1129
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-1778420920-REIHI3S7643QTHvNpcCC"
session_id
(null)
api_type
"completions"
id
"gen-1778420920-Z3z3pZnZMJbf7qUaSN7N"
upstream_id
"chatcmpl-81896370805aa30c"
total_cost
0.00010628
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
99.52%
Dialogue to Total Word Ratio
Ratio: 12.63%, Deviation: 2.63%
neededClean
false
wordsTotal
190
wordsDialogue
24
79.8984%