NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8WZT04Q5KDXDMT9WF09FH2
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.9s
Cost:
$0.000102
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
98.67%
Dialogue to Total Word Ratio
(details)
92.5257%
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 telling me the target is a six-year-old’s birthday bash?" Molly hissed, checking her lockpicks. "It is the perfect cover, Molly! Low security, high reward," Bill whispered back, adjusting his oversized clown nose. "The reward is a pile of plastic dinosaurs and half-eaten cupcakes, Bill." "Not if the parents are high-society! There could be iPads, high-end robotics, perhaps a miniature drone!" "We are professional jewel thieves. Not party crashers." "It is a tactical infiltration! We wear the masks, we blend in, we grab the loot." "You are wearing polka dots. You look like a walking target." "It is camouflage! No one suspects a man in a rainbow wig." "And the cake? Is the cake part of the heist?" "I refuse to steal a lemon sponge, Molly. Have some professional dignity." "Just focus. We enter through the bouncy castle, navigate the sugar-high obstacle course, and exit via the sandbox." "The sandbox? That is amateur hour." "It is the only blind spot in the backyard!" "Fine. But if a toddler asks me to play hide-and-seek, I am abandoning the mission." "Deal. Now, grab the glitter grenades. We move at teatime."
created_at
"2026-05-10T12:14:58.571Z"
5/10/2026, 12:14:58 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
107
moderation_latency
(null)
generation_time
4744
tokens_prompt
77
tokens_completion
309
native_tokens_prompt
79
native_tokens_completion
285
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
0.00010243
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-RjFGAM2UGwM2HjbZrK9xVbOl"
is_byok
false
latency
46
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-1778415298-KVADCWDEMK0BxbytepO1"
session_id
(null)
api_type
"completions"
id
"gen-1778415298-fITThlDVa8CCZEP0cxSQ"
upstream_id
"chatcmpl-RjFGAM2UGwM2HjbZrK9xVbOl"
total_cost
0.00010243
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
98.67%
Dialogue to Total Word Ratio
Ratio: 93.40%, Deviation: 3.40%
neededClean
false
wordsTotal
197
wordsDialogue
184
92.5257%