NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8WSRSC9X83V7Y13BBVPDWD
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.3s
Cost:
$0.000092
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
99.41%
Dialogue to Total Word Ratio
(details)
59.7980%
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
"Is that a clown nose in your pocket, Bill?" Molly whispered, glaring at him through the binoculars. "It is tactical camouflage," Bill hissed back. "No one suspects the entertainer." "We are here for the loot, not to juggle for toddlers," she snapped. "The target is the mountain of wrapped boxes by the bouncy castle. Clear?" "Crystal. But the perimeter is guarded by a very aggressive golden retriever." "Can you bypass a dog?" "I can distract him with a piece of premium jerky." "Focus! What about the parents? They’re hovering like vultures over the snack table." "I’ll blend in. I’ll pretend to be an eccentric uncle who loves finger foods and bad puns." "And the getaway?" "The van is idling behind the sandbox. We grab the ribbons, avoid the glitter bombs, and vanish before the cake is cut." "And if a kid asks for a balloon animal?" "I will tell them my artistic integrity won't allow it." "God, you're terrible at this." "I am a professional, Molly. Now, pass me the face paint. The polka dots are essential for my infiltration."
created_at
"2026-05-10T12:11:40.723Z"
5/10/2026, 12:11:40 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
296
moderation_latency
(null)
generation_time
4196
tokens_prompt
77
tokens_completion
285
native_tokens_prompt
79
native_tokens_completion
255
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
0.00009223
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-RPGr5iK1J3OqzpXIVOPvxwLE"
is_byok
false
latency
44
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-1778415100-yVeX6pcTH1dtcSLoMwmT"
session_id
(null)
api_type
"completions"
id
"gen-1778415100-RNsk33FlLpmuhysYEbAA"
upstream_id
"chatcmpl-RPGr5iK1J3OqzpXIVOPvxwLE"
total_cost
0.00009223
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
99.41%
Dialogue to Total Word Ratio
Ratio: 92.78%, Deviation: 2.78%
neededClean
false
wordsTotal
180
wordsDialogue
167
59.7980%