NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZD4E2P75NW4YGZJAGWGGZ
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.5s
Cost:
$0.000088
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
64.54%
Dialogue to Total Word Ratio
(details)
77.5116%
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 adjusted her tactical goggles, which were currently obscuring her vision of the bouncy castle. She tapped a blueprint of the suburban backyard, pointing a gloved finger at the pile of brightly wrapped boxes near the sandbox. The target was massive, a mountain of glitter-covered cardboard and high-end electronics. Bill squinted at the perimeter, his stomach growling loudly enough to rival a security alarm. He was currently wearing a poorly fitted dinosaur onesie to blend in with the guest list. The sheer amount of sugar in the air felt like a physical barrier to their progress. “Is that a remote-controlled drone in the blue box?” Bill whispered, his eyes widening with greed. “Focus, Bill,” Molly hissed, checking her watch. “We hit the gift pile during the cake cutting. That’s when the chaos peaks.” “What if we get distracted by the juice boxes?” he asked nervously. Molly rolled her eyes and tightened her utility belt, which was currently loaded with extra napkins and a small crowbar. The mission required surgical precision, not snack breaks. They crouched behind a giant inflatable flamingo, waiting for the first birthday song to signal their strike.
created_at
"2026-05-10T12:57:12.395Z"
5/10/2026, 12:57:12 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
486
moderation_latency
(null)
generation_time
5351
tokens_prompt
77
tokens_completion
307
native_tokens_prompt
79
native_tokens_completion
243
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
0.00008815
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-R9n8ONIYybfcTVXYDzWBVgvI"
is_byok
false
latency
415
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778417832-a6Dkz9bvgO2UXiRgEcKD"
session_id
(null)
api_type
"completions"
id
"gen-1778417832-bFAetJFBApjvd6l6W3a4"
upstream_id
"chatcmpl-R9n8ONIYybfcTVXYDzWBVgvI"
total_cost
0.00008815
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
64.54%
Dialogue to Total Word Ratio
Ratio: 18.13%, Deviation: 8.13%
neededClean
false
wordsTotal
193
wordsDialogue
35
77.5116%