NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8WSK8NB1GSZNJTBWVC4CN9
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.1s
Cost:
$0.000082
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
87.5716%
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 crouched behind a plastic pink flamingo, squinting through her binoculars at the suburban fortress. The target was a high-stakes tactical environment: a seventh birthday party for a child named Leo, who possessed an alarming surplus of high-end electronics and LEGO sets. The perimeter was guarded by three toddlers in dinosaur costumes and a very judgmental golden retriever. Bill adjusted his tactical turtleneck, which was unfortunately a bright neon yellow, making him look less like a master thief and more like a human high-visibility vest. He checked his watch with practiced intensity, oblivious to the juice box staining his sleeve. "The bouncy castle provides perfect tactical cover for the extraction," Molly whispered, pointing toward the inflatable obstacle course. "I am more concerned about the clown," Bill replied, eyeing the man currently making balloon animals near the buffet. Molly rolled her eyes, mapping out the trajectory from the snack table to the pile of unwrapped gadgets. The mission required surgical precision and a complete lack of conscience. They would strike during the cake ceremony, utilizing the chaos of sugar rushes to vanish into the night with the loot.
created_at
"2026-05-10T12:11:35.071Z"
5/10/2026, 12:11:35 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
92
moderation_latency
(null)
generation_time
5382
tokens_prompt
77
tokens_completion
306
native_tokens_prompt
79
native_tokens_completion
226
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
0.00008237
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-RUpYF6gQiIu7EK9iLZflWS4u"
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-1778415095-X6NYOsd9ofdxcRQLIZIf"
session_id
(null)
api_type
"completions"
id
"gen-1778415095-eE53MnTFlLope0sOyTii"
upstream_id
"chatcmpl-RUpYF6gQiIu7EK9iLZflWS4u"
total_cost
0.00008237
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
99.99%
Dialogue to Total Word Ratio
Ratio: 8.95%, Deviation: 1.05%
neededClean
false
wordsTotal
190
wordsDialogue
17
87.5716%