NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR9322GK7FFC3Q5XV4403WE7
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 12s
Cost:
$0.000988
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
90.45%
Dialogue to Total Word Ratio
(details)
52.3765%
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
"The target is the Smith residence. Timing is absolutely critical," Molly stated, pointing at the map. "Wait, why on earth are we robbing a six-year-old?" Bill asked. "He's not just a kid; he's the heir to a global toy empire. The gifts are high-end prototypes." "High-end Legos? Who actually steals Legos?" "Collectors, Bill. Serious, adult collectors with deep pockets. Now, the distraction is a fake clown." "I'm not wearing the nose. Absolutely not." "You're wearing the nose. I'll be the magic balloon artist infiltrating the gift table while you juggle." "What about the security?" "A sleepy golden retriever and a very confused grandmother. We strike exactly during the cake cutting." "Will there be cake for us? I'm starving." "Focus! We move in at two, sweep the entire pile, and vanish before the piñata bursts." "If I see a piñata, I'm hitting it. I cannot resist the sugar." "Professionalism, Bill! For the love of all that is criminal, be professional." "Can I at least keep one small toy? Just a tiny one?" "No." "Fine. But I'm definitely keeping the nose."
created_at
"2026-05-10T14:01:04.282Z"
5/10/2026, 2:01:04 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
355
moderation_latency
(null)
generation_time
131422
tokens_prompt
77
tokens_completion
2265
native_tokens_prompt
82
native_tokens_completion
2573
native_tokens_completion_images
(null)
native_tokens_reasoning
1984
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
0.0009884
router
(null)
provider_responses
0
endpoint_id
"29b94af5-d8f8-419a-9cf1-ae1f2831142b"
is_byok
false
latency
106
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Venice"
status
429
1
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RlKqRh5LEsojrdn1WsY6qhPd"
is_byok
false
latency
60
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-1778421664-oNKcKj5pMAtS1F0znTHY"
session_id
(null)
api_type
"completions"
id
"gen-1778421664-hmwgpKAOuTqNgLA9CSbA"
upstream_id
"chatcmpl-RlKqRh5LEsojrdn1WsY6qhPd"
total_cost
0.0009884
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
14.30%
Matches word count
n/a
neededClean
false
words
179
90.45%
Dialogue to Total Word Ratio
Ratio: 95.63%, Deviation: 5.63%
neededClean
false
wordsTotal
183
wordsDialogue
175
52.3765%