NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR94686TQ894CHWTWYC1FV7N
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6m 13s
Cost:
$0.004680
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9592%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 spread the stolen blueprint across the grease-stained table, her eyes narrowed in intense, professional focus. "The target is the Miller residence, specifically the backyard bouncy castle zone," she whispered. Bill squinted at the colorful, glitter-covered map, a look of profound, existential hesitation crossing his rugged, scarred face. "Wait, we're hitting a birthday party? That's low, even for us." Molly tapped a heavy finger on a drawing of a giant, inflatable dinosaur. "It’s high reward, Bill! Look at the intel. There’s a new LEGO set and a mountain of remote-controlled cars." Bill rubbed his chin, sweating profusely under the dim, flickering light of their cramped, basement hideout. "But what about the sentries? The toddlers are unpredictable. They have no concept of stealth." Molly leaned in closer, her voice dropping to a conspiratorial, dangerous hiss. "We use the distraction maneuver. You dress as a clown. I’ll blend in as the disgruntled aunt." Bill gasped, clutching his chest in mock, dramatic agony. "A clown? My face is too expressive for greasepaint!" Molly rolled her eyes and snapped, "Just pull your nose and keep your mouth shut. We hit the gift table during the cake ceremony." They both stared at the map in heavy, weighted silence.
created_at
"2026-05-10T14:20:49.785Z"
5/10/2026, 2:20:49 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
230
moderation_latency
(null)
generation_time
372629
tokens_prompt
77
tokens_completion
10317
native_tokens_prompt
82
native_tokens_completion
13749
native_tokens_completion_images
(null)
native_tokens_reasoning
9996
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
0.0046804
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-RXZlmE3JVyt2gbXQ4fBZFbPl"
is_byok
false
latency
112
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778422849-7TM0KxmKPMQoFbn9bZn7"
session_id
(null)
api_type
"completions"
id
"gen-1778422849-sVmTiJHjRlDpANknpOrF"
upstream_id
"chatcmpl-RXZlmE3JVyt2gbXQ4fBZFbPl"
total_cost
0.0046804
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
100.00%
Dialogue to Total Word Ratio
Ratio: 49.51%, Deviation: 0.49%
neededClean
false
wordsTotal
206
wordsDialogue
102
99.9592%