NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YTDMXHFBHF3VH5FH76B1V
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 49s
Cost:
$0.002109
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
96.99%
Dialogue to Total Word Ratio
(details)
86.0746%
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 to the map. "Alright, the cake is the primary distraction." "Wait, we're really stealing from six-year-olds?" Bill asked. "Low risk, high reward, Bill. Those discontinued Lego sets are gold on the secondary market." "What about the clowns?" "I've mapped the clown's rotation. He’s occupied with balloon animals from 2 to 3. That's our tactical window." "And the juice boxes? Should we secure the refreshments?" "Ignore the juice. We hit the gift table, bag the toys, and exit through the dog door." Bill frowned. "I'm far too large for a dog door, Molly." "Then suck it in. Do you want the limited edition dinosaur or not?" "Is it the T-Rex with the laser eyes?" "Exactly. Now, focus." "I'm in. What's the signal?" "The moment the birthday boy starts crying, we move." "That's cold. I love it." "Now, check your disguise." "Is this tutu too much? I feel like it's a bit loud." "It's a themed children's party, Bill. You have to blend in." "I just think the sequins are distracting." Molly sighed. "The sequins are the perfect camouflage. Now, grab the burlap sacks and let's go."
created_at
"2026-05-10T12:46:59.239Z"
5/10/2026, 12:46:59 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
153
moderation_latency
(null)
generation_time
229150
tokens_prompt
77
tokens_completion
4037
native_tokens_prompt
82
native_tokens_completion
5522
native_tokens_completion_images
(null)
native_tokens_reasoning
3731
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
0.00210902
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RhYIHFuZVTFzy9LgpxyybIaA"
is_byok
false
latency
52
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-1778417219-Q1TTJOlcQZL3EcSQs3Bu"
session_id
(null)
api_type
"completions"
id
"gen-1778417219-i2SRSebygsx3UbadUpNB"
upstream_id
"chatcmpl-RhYIHFuZVTFzy9LgpxyybIaA"
total_cost
0.00210902
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
96.99%
Dialogue to Total Word Ratio
Ratio: 94.18%, Deviation: 4.18%
neededClean
false
wordsTotal
189
wordsDialogue
178
86.0746%