NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFG3NGN0VTRXP0H5DZC8VW7
Run Details
Model:
Nemotron 3 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 5s
Cost:
$0.001552
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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: Okay, Bill, the party starts at three, but the host leaves the cake unattended at three‑ten. Bill: Got it. I’ll slip the keycard from the coat rack while you grab the gift table. Molly: We need the glitter confetti to cover any squeaky shoes. Bill: Already packed in my pocket, ready to toss when the kids chant 'Happy birthday!' Molly: The balloons hide the door; we’ll pop two and slip inside. Bill: I’ll knock over the punch bowl to create chaos. Molly: Perfect distraction. We’ll snatch the presents in under five minutes. Bill: I’ll stuff the loot into the backpack, then we’ll exit through the garden gate. Molly: Meet me by the old oak at five, no witnesses. Bill: Deal. If anyone asks, we were just playing hide‑and‑seek. Bill: The kids will be busy blowing the birthday candles, giving us a perfect window. Molly: I’ll slip the ribbon off the ribbon‑wrapped box and slide it into my bag. Bill: Don’t forget the secret stash behind the cake; it’s the biggest loot. Molly: We can split the loot evenly, half each, before the sheriff shows up. Bill: If we hear a squeak, we’ll silence it with a quick pop of
created_at
"2026-03-11T22:26:05.475Z"
3/11/2026, 10:26:05 PM
model
"nvidia/nemotron-3-nano-30b-a3b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
455
moderation_latency
(null)
generation_time
124952
tokens_prompt
77
tokens_completion
6588
native_tokens_prompt
82
native_tokens_completion
7740
native_tokens_completion_images
(null)
native_tokens_reasoning
6297
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
(null)
native_finish_reason
(null)
usage
0.0015521
router
(null)
provider_responses
0
endpoint_id
"2bd3912d-8b35-4818-b873-24ccfefa6cf9"
id
"chatcmpl-RffTNTpqAOD6L4muQglCvOpx"
is_byok
false
latency
56
model_permaslug
"nvidia/nemotron-3-nano-30b-a3b"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773267965-aGD5rrMITpRtWkJgvFcA"
upstream_id
"chatcmpl-RffTNTpqAOD6L4muQglCvOpx"
total_cost
0.0015521
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 7.00%, Deviation: 83.00%
neededClean
false
wordsTotal
200
wordsDialogue
14
50.0000%