NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8WMKPBPMYN3NBJCV0XF00T
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
18.7s
Cost:
$0.000125
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.9120%
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
"Are you sure about the costumes, Bill?" "Positive. Who suspects two oversized garden gnomes?" "We'll look like creeps, Bill. Absolute creeps." "Exactly! We blend in with the lawn ornaments. It's tactical camouflage." "It's a five-year-old's birthday party, not a covert op in the jungle." "Focus, Molly. What's the status on the cake?" "The distraction? I've rigged the frosting to collapse at precisely two o'clock." "Brilliant. While the toddlers are fighting over buttercream, we swoop the gift table." "And the security?" "A golden retriever named Buster. I've got a pocket full of premium organic treats." "You’re bribing a dog?" "It's called diplomacy, Molly." "And if the parents catch us?" "We freeze. Gnomes don't move, remember?" "I can't believe I'm risking jail time for a pile of LEGO sets and Barbie Dreamhouses." "Hey, those sets have a high resale value on eBay." "You're a lunatic." "I'm a visionary. Now, help me into this ceramic hat; it's pinching my ears." "Fine. But if we get chased by a mob of sugar-high children, I'm tripping you." "Fair deal."
created_at
"2026-05-10T12:08:51.666Z"
5/10/2026, 12:08:51 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
400
moderation_latency
(null)
generation_time
18647
tokens_prompt
77
tokens_completion
302
native_tokens_prompt
79
native_tokens_completion
301
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
0.00012465
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RUVAuxWTAAQz2pJEt2w5k5K4"
is_byok
false
latency
50
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778414931-KRVPTW7hDmCjIIAcaqa4"
session_id
(null)
api_type
"completions"
id
"gen-1778414931-OcghiP339QYqXGGnMqMl"
upstream_id
"chatcmpl-RUVAuxWTAAQz2pJEt2w5k5K4"
total_cost
0.00012465
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
174
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
177
wordsDialogue
177
18.9120%