NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZT1E02ZAKN07KR6E4FZWJ
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 21s
Cost:
$0.001065
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
44.3567%
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
"Listen, Bill, the target is a six-year-old's birthday bash." "A birthday party? Really, Molly? This is a new low for us." "High yield, low security, Bill. Think of the limited edition LEGO sets!" "But children are chaotic. They're like tiny, screaming landmines." "That's why we go in as the professional entertainment. We're the 'Magic Balloon Duo'." "I can't do balloons." "You can blow air into a latex tube, Bill. It's not rocket science." "I have a phobia of popping sounds! It's a genuine medical condition!" "Toughen up. We hit the gift table during the cake frenzy." "What if the parents suspect us?" "Who suspects a man in a glittery cape? Just keep the distractions going." "Do I really have to wear the sequins?" "Yes, Bill. Sequins are the cloak of invisibility for party clowns." "Fine. But I'm taking a full cut of any Nintendo Switch we find." "Deal. Now, practice your 'Ta-da!' face." "Ta-da." "Pathetic. More enthusiasm!" "Ta-da!" "Better. Now, let's go steal some plastic dinosaurs and a few remote-control cars." "I still hate balloons." "Just keep your mouth shut and your cape sparkly."
created_at
"2026-05-10T13:04:15.304Z"
5/10/2026, 1:04:15 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
189
moderation_latency
(null)
generation_time
80606
tokens_prompt
77
tokens_completion
2602
native_tokens_prompt
82
native_tokens_completion
2775
native_tokens_completion_images
(null)
native_tokens_reasoning
2310
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
0.00106516
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RS6RQTNDV9VyLC05tDNU1mG0"
is_byok
false
latency
54
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-1778418255-H6G1O9YiJaAsiGOhpIgo"
session_id
(null)
api_type
"completions"
id
"gen-1778418255-jRhS4tTIOtnHUib0laQl"
upstream_id
"chatcmpl-RS6RQTNDV9VyLC05tDNU1mG0"
total_cost
0.00106516
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
190
wordsDialogue
190
44.3567%