NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR902G39CGPWRK1EMHGV7P30
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11m 20s
Cost:
$0.007172
Provider:
Novita
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 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 spread the glitter-encrusted invitation across the grease-stained table. The target was Timmy’s fifth birthday extravaganza, a fortress of bouncy castles and juice boxes. She traced the layout of the living room with a laser pointer, highlighting the suspicious pile of brightly wrapped boxes near the dessert table. Bill leaned in, his face illuminated by the dim glow of a half-eaten donut. He adjusted his tactical turtleneck, which was slightly too tight around his midsection. The mission required absolute stealth and an immunity to strawberry frosting. They needed to bypass the perimeter of hyperactive toddlers and the dreaded sensory overload of a bubble machine. Molly pointed to the gift pile, her eyes narrowed with professional intensity. The logistics were complex, involving a diversionary tactic using a rogue balloon animal to distract the sugar-fueled guards. Bill squinted at the map, looking skeptical of the high-stakes glitter situation. He wiped frosting from his lip and sighed deeply. He looked quite nervous and adjusted his glasses. "Is a plastic unicorn really worth this extreme risk?" Molly glared at him. "It is about the pure, unadulterated thrill, Bill. Stop whining now." They both knew the real prize was the limited edition dinosaur toy set.
created_at
"2026-05-10T13:08:52.467Z"
5/10/2026, 1:08:52 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9408
moderation_latency
(null)
generation_time
679936
tokens_prompt
77
tokens_completion
13218
native_tokens_prompt
81
native_tokens_completion
17904
native_tokens_completion_images
(null)
native_tokens_reasoning
12896
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
0.00717213
router
(null)
provider_responses
0
endpoint_id
"03b96766-ef7e-454f-9519-c76b70654b49"
id
"210f880c1d0d8c9c8e3d2f83f5bdea6e"
is_byok
false
latency
9086
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778418532-fWTmoi1BjIYVg54e50OI"
session_id
(null)
api_type
"completions"
id
"gen-1778418532-Nfh68ZdO5YqV0bRVti1R"
upstream_id
"210f880c1d0d8c9c8e3d2f83f5bdea6e"
total_cost
0.00717213
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
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: 9.76%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
20
100.0000%