NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-19-01M7SP4SRMCDWQFZYDEAVZ00VS
Run Details
Model:
Gemini 4 Neon (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.8s
Cost:
$0.027861
Provider:
Google
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
99.8989%
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
Molly pointed at the crayon blueprint. "We hit the bouncy castle at fourteen hundred hours," she said. "Isn't that just two o'clock?" Bill asked. "Focus, Bill. The clowns are a distraction. The real perimeter is the moms with wine tumblers. They have eyes in the back of their heads." "What about the dad on the grill?" "Harmless. He's too busy asserting dominance over the hot dogs. Once the cake comes out, the kids will swarm the patio. That's our window." "And we grab the loot?" "Every single wrapped box. I heard little Timmy's uncle works at a tech startup. There's a high probability of a gaming console in that pile." "What if it's just socks?" "Nobody buys a six-year-old socks, Bill. Have some faith. Now, do you have the disguises?" "Right here." Bill held up two oversized tutus. "Why tutus?" "The invitation said princess theme. You want to blend in, right?" "I'm a six-foot-tall woman with a crowbar, Bill. A tutu isn't going to make me invisible." "It will if you twirl." "Fine. Give me the pink one. If we get caught by a bunch of toddlers, I'm blaming you." "Deal. Just promise me we're taking the piƱata, too."
created_at
"2026-11-19T10:37:54.847Z"
11/19/2026, 10:37:54 AM
model
"google/gemini-4-neon-20261118"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1659
moderation_latency
(null)
generation_time
16792
tokens_prompt
75
tokens_completion
788
native_tokens_prompt
97
native_tokens_completion
1838
native_tokens_completion_images
0
native_tokens_reasoning
1522
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
"default"
usage
0.027861
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1795084674-4iM0QPH8eWY3ObW9vp6s"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1795084674-2k3jw75EcBwz0FBUXRLs"
upstream_id
"gtH-atLmOdmB9LsP-9fagAY"
provider_responses
0
endpoint_id
"cbc1d01f-e431-41ec-9abb-36c1a5b10cb4"
id
"gtH-atLmOdmB9LsP-9fagAY"
is_byok
false
latency
1659
model_permaslug
"google/gemini-4-neon-20261118"
provider_name
"Google"
status
200
total_cost
0.027861
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
99.80%
Dialogue to Total Word Ratio
Ratio: 92.12%, Deviation: 2.12%
neededClean
false
wordsTotal
203
wordsDialogue
187
99.8989%