NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM095D2TS5D9MT07927KCN5B
Run Details
Model:
GPT-5.4 Nano (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.0s
Cost:
$0.002883
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
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: Bill, tonight we rob a children’s party. Bill: I brought the tiny crowbar, for tiny trouble. Molly: No crowbar. Sympathy face and steal with style. Bill: I practiced the sympathy face with tears and glitter. Molly: Good. Hide behind the dinosaur balloons. Bill: Which dinosaur ones—the squeaky or the squeaky with teeth? Molly: The squeaky with teeth. The DJ’s on “Baby Shark,” so nobody looks. Bill: I can steal presents while doing the floss, right? Molly: Just don’t floss on the cake. Frost is expensive and judgmental. Bill: Fine. What’s our entry point? Molly: The gift-wrapping table. Everyone assumes it’s magical. Bill: I’m terrifying with my sleeves and my mysterious snacks. Molly: We take only presents. Leave the germs, leave the cupcakes. Bill: The cupcakes are screaming. Molly: Ignore the cupcakes. On my signal, we swap name tags and walk out as “Gift Ambassadors.” Bill: If a kid asks, we say we’re delivering extra surprises. Molly: Shh—birthday boy’s staring at our shoes. Bill: My shoes are innocent! Mostly. Molly: If security asks, nod slowly and offer balloons. Bill: I can juggle keys. Molly: No, just hold the sack like you’re late for gift wrapping and smile, the cheap kind.
created_at
"2026-03-18T10:51:47.688Z"
3/18/2026, 10:51:47 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11874
moderation_latency
(null)
generation_time
12327
tokens_prompt
77
tokens_completion
959
native_tokens_prompt
66
native_tokens_completion
2296
native_tokens_completion_images
0
native_tokens_reasoning
1975
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
"stop"
native_finish_reason
"completed"
usage
0.0028832
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_006926f929d1230c0169ba83c3c4c88193b3147e73eb9bcc6b"
is_byok
false
latency
227
model_permaslug
"openai/gpt-5.4-nano-20260317"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773831107-YwLD3SfMCNwJlkcKALha"
upstream_id
"resp_006926f929d1230c0169ba83c3c4c88193b3147e73eb9bcc6b"
total_cost
0.0028832
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
0.00%
Dialogue to Total Word Ratio
Ratio: 1.97%, Deviation: 88.03%
neededClean
false
wordsTotal
203
wordsDialogue
4
49.9920%