NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR922QRJGDBV0G4HTGH517DN
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.3s
Cost:
$0.000097
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
28.4888%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"We are not robbing a bouncy castle, Bill." "It is not just a bouncy castle, Molly. It is a tactical infiltration of a high-stakes social gathering." "It is a five-year-old’s birthday party. The security is a tired mother and a clown who smells like gin." "Exactly! The perfect cover. The chaos of the sugar rush provides the ultimate diversion." "And the target?" "The gift pile. It is a goldmine of Lego sets, remote-controlled cars, and those handheld electronic games. It is pure, unadulterated consumerist joy ripe for the taking." "We look ridiculous in these dinosaur onesies." "They are high-visibility camouflage! Nobody suspects a triceratops of grand larceny." "I feel a draft in the tail." "Focus! When the cake comes out, we move. You grab the big boxes, I scoop the small ones into the diaper bag." "A diaper bag? Really?" "It is inconspicuous! Nobody questions a woman carrying a diaper bag." "Fine. But if I have to sing Happy Birthday, I am out." "Deal. Now, tuck in your snout. The piñata is about to be struck. That is our signal."
created_at
"2026-05-10T13:43:57.465Z"
5/10/2026, 1:43:57 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3553
moderation_latency
(null)
generation_time
19182
tokens_prompt
77
tokens_completion
287
native_tokens_prompt
79
native_tokens_completion
269
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
0.00009699
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-R4uc4pEkCBTBVgmrDfxYpCVw"
is_byok
false
latency
49
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-1778420637-mGsXYoUL29jjzwXQVTLN"
session_id
(null)
api_type
"completions"
id
"gen-1778420637-aEIM7H4W76GLu35nMFhI"
upstream_id
"chatcmpl-R4uc4pEkCBTBVgmrDfxYpCVw"
total_cost
0.00009699
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
185
wordsDialogue
185
28.4888%