NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YZ4C80B0J3K5Y3PQRF02J
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.1s
Cost:
$0.000088
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
45.2446%
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 tutu, glaring at the blueprints spread across the sticky kitchen table. "We strike during the bouncy castle climax, Bill." "The bouncy castle?" Bill squeaked, adjusting his oversized clown nose. "That sounds structurally unsound for a professional heist." "It is the perfect diversion," Molly insisted, pointing to a cluster of brightly wrapped boxes. "While the toddlers are distracted by the sugar crash, we swoop in and bag the loot." "But what about the birthday boy?" Bill whispered, eyeing a suspicious pile of party hats. "He has the eyes of a hawk. A tiny, sticky-fingered hawk." "Focus, Bill! We aren't here for cake. We are here for the high-end electronics hidden in those teddy bears." "I thought we were stealing the LEGO sets," Bill muttered, checking his utility belt filled with juice boxes. "LEGOs are too heavy for a quick getaway," Molly snapped. "Check your perimeter. Are the balloon animals deployed?" "Ready and waiting," Bill replied, saluting with a cocktail sausage. "But if a clown catches us, I'm blaming your tactical tutu." "Just grab the gift bags and stay low," Molly commanded. "Operation Cupcake is officially a go."
created_at
"2026-05-10T12:49:33.586Z"
5/10/2026, 12:49:33 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
209
moderation_latency
(null)
generation_time
3799
tokens_prompt
77
tokens_completion
309
native_tokens_prompt
79
native_tokens_completion
266
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
0.0000877
router
(null)
provider_responses
0
endpoint_id
"e2a16fa6-1f65-413e-9ecb-93901089ddb1"
id
"id-1778417373743"
is_byok
false
latency
153
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Cloudflare"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778417373-4ipxXbAU467GvQxPIKdR"
session_id
(null)
api_type
"completions"
id
"gen-1778417373-LNARxMJzsmh5CHqYEUaP"
upstream_id
"id-1778417373743"
total_cost
0.0000877
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
0.01%
Dialogue to Total Word Ratio
Ratio: 67.71%, Deviation: 17.71%
neededClean
false
wordsTotal
192
wordsDialogue
130
45.2446%