NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XHRSA24HSDSA9FPA1M41A
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 10s
Cost:
$0.003919
Provider:
Cloudflare
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-coated blueprint across the grease-stained table. The tactical diagram featured a high-stakes obstacle course of bouncy castles, balloon animals, and lukewarm juice boxes. She pointed a laser at the primary target: a mountain of brightly wrapped boxes positioned precariously under a weeping willow. The perimeter was heavily guarded by a relentless force of hyperactive toddlers and a very confused golden retriever named Barnaby. Bill adjusted his night-vision goggles, which were actually just cheap swimming goggles painted black. He squinted intensely at the layout of the smash cake station, noting the high risk of frosting-based casualties. The mission required surgical precision and absolute silence, qualities neither of them possessed. Molly tapped the center of the map, her eyes narrowing with professional intensity. "The nap time window is our only single real shot, Bill," Molly whispered. "But what if the very scary clown catches us?" Bill asked. She ignored him, focusing instead on the extraction route through the sandbox. Every second counted before the inevitable sugar crash hit the target zone. They had to move fast, grab the LEGO sets, and vanish into the night before the parents noticed the missing stuffed dinosaurs. It was their most perfect heist.
created_at
"2026-05-10T12:24:47.155Z"
5/10/2026, 12:24:47 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
125
moderation_latency
(null)
generation_time
189905
tokens_prompt
77
tokens_completion
9500
native_tokens_prompt
81
native_tokens_completion
13036
native_tokens_completion_images
(null)
native_tokens_reasoning
9168
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
0.0039189
router
(null)
provider_responses
0
endpoint_id
"e2a16fa6-1f65-413e-9ecb-93901089ddb1"
id
"id-1778415887244"
is_byok
false
latency
90
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-1778415887-6r0D1NRgeeFRxEHkN5if"
session_id
(null)
api_type
"completions"
id
"gen-1778415887-54lRwEB7I5EUKwqXuoUx"
upstream_id
"id-1778415887244"
total_cost
0.0039189
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
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%