NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHVPC6AWKGDPNGTKSK10DQPK
Run Details
Model:
Gemini 3.1 Pro (Preview)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 53s
Cost:
$0.115586
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 utterly oversized clown shoes. They pinched terribly, but blending in at a seventh birthday bash required a serious commitment to latex and face paint. Bill sat across the cramped getaway van, attempting to twist a neon balloon into a recognizable animal. It currently resembled a distressed sausage. The blueprint of the community center was taped to the dashboard, decorated with aggressive red marker circles around the primary targets. The mascot was the distraction, but the mountain of brightly wrapped gifts teetering recklessly on the folding table was the true prize. They were professionals, accustomed to cracking safes and dodging lasers, not avoiding sticky toddlers smelling of fruit juice. Yet, times were tough and shiny robot toys had immense street value. Bill checked his oversized pocket watch, a prop that doubled as a timer. The sugar rush would peak in precisely four minutes. Once the greedy children swarmed the massive and sweet sheet cake, the cardboard gift perimeter would be entirely exposed. Molly asked quietly, "Do we have the extraction route planned?" Bill quickly replied, "Yes. Avoid the bouncy castle. Grab those wrapped presents now." She then firmly loaded her shiny lockpicks and finally said, "Let us go."
created_at
"2026-02-19T19:35:05.657Z"
2/19/2026, 7:35:05 PM
model
"google/gemini-3.1-pro-preview-20260219"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4613
moderation_latency
(null)
generation_time
112462
tokens_prompt
77
tokens_completion
4080
native_tokens_prompt
67
native_tokens_completion
9621
native_tokens_completion_images
0
native_tokens_reasoning
9385
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.115586
router
(null)
provider_responses
0
endpoint_id
"2abf5677-0826-45d9-8470-3d62c31d54a1"
is_byok
false
latency
4612
model_permaslug
"google/gemini-3.1-pro-preview-20260219"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771529705-v1xTzHBTTwnDoJlxyl7P"
upstream_id
(null)
total_cost
0.115586
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%