NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A8X8Y39SKM94ESNWMMQ2Y
Run Details
Model:
GPT-5.4 Nano (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
17.6s
Cost:
$0.003109
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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, the kid party is tonight, right? Bill: Yeah, sprinkles and chaos. Parents will be watching the clown. Molly: Perfect. We'll grab every present before anyone says “Who ordered the pony?” Bill: Don’t say pony. What’s the entry plan? Molly: Disguise kit. You wear the mascot head. Bill: I hate it. It makes my eyebrows sweat. Molly: Sweat quietly. Borrow the room map from the cake table. Bill: How? Molly: You compliment the frosting like you’re applying for a job. Bill: “Wow, this frosting is suspiciously competent.” Molly: Step two: my kid-safe lockpick. Bill: It’s a spoon, isn’t it? Molly: A trusting spoon. It persuades locks. Bill: Locks don’t have feelings. Molly: Everyone does—except the security guard, asleep in a folding chair. Bill: If he wakes up, we’ll offer a cupcake. Molly: Lemon filling. He’s allergic. Bill: What about the treehouse fort? Molly: Bubble-gum tunnel. Then socks last—if there are any. Bill: You’re monstrous. Molly: Festive. Hush—someone’s singing “Happy Birthday”! Bill: After the song, we sprint. No heroics. Molly: Obvious. We’ll stash the loot in the gift-wrapping bin. Bill: What about the wrapping paper? Molly: We’ll “accidentally” give them glitter. Bill: Deal. And I’ll steal the big bow, too.
created_at
"2026-03-18T11:11:11.148Z"
3/18/2026, 11:11:11 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15127
moderation_latency
(null)
generation_time
16984
tokens_prompt
77
tokens_completion
1007
native_tokens_prompt
66
native_tokens_completion
2477
native_tokens_completion_images
0
native_tokens_reasoning
2116
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
0.00310945
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_0a5b40b06cd049720169ba884f3890819394e84d2284a475b6"
is_byok
false
latency
197
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-1773832271-vRQDSnjuWMPBv104j9mz"
upstream_id
"resp_0a5b40b06cd049720169ba884f3890819394e84d2284a475b6"
total_cost
0.00310945
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
0.00%
Dialogue to Total Word Ratio
Ratio: 6.31%, Deviation: 83.69%
neededClean
false
wordsTotal
206
wordsDialogue
13
49.9595%