NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ032BECA3JKMX32X3WK1SHQ
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 12s
Cost:
$0.003105
Provider:
WandB
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
94.28%
Dialogue to Total Word Ratio
(details)
97.1418%
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 and Bill crouch behind the bright banner, whispering about the party, kids' laughter fills air softly tonight. Molly: "We go in through the candy table, right?" Bill: "Exactly, the sugar clouds mask our entrance." Molly: "What about the clown? He’s got a red nose that could spot us." Bill: "We’ll distract him with a squeaky balloon—he can’t resist." Molly: "And the kids? They’re like tiny security cameras." Bill: "We’ll slip a bedtime story onto the speaker, lull them." Molly: "How long before the parents notice the missing gifts?" Bill: "Long enough to unload everything into the van." Molly: "Do we need masks?" Bill: "A banana peel on our faces works better than any mask." Molly: "Alright, I’ll bring the banana stash." Bill: "I’ll snag the glitter confetti cannon for cover." Molly: "We should time it with the cake cutting." Bill: "When the cake’s up, everyone’s looking up." Bill: "The kids will be too busy chasing balloons, scooping cake, and singing happy birthday, completely oblivious to our loot." Molly: "Perfect, we pop the cannon, chaos, and we grab." Bill: "Then we sprint to the gate, ditch the loot, and vanish." Molly: "And no one will ever suspect a banana‑masked thief."
created_at
"2026-04-24T15:52:21.718Z"
4/24/2026, 3:52:21 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
261
moderation_latency
(null)
generation_time
72262
tokens_prompt
77
tokens_completion
4781
native_tokens_prompt
125
native_tokens_completion
5144
native_tokens_completion_images
(null)
native_tokens_reasoning
4457
native_tokens_cached
64
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"
usage
0.00310515
router
(null)
provider_responses
0
endpoint_id
"3ca6292f-cef7-48a2-bf52-988e934cab57"
id
"chatcmpl-bd02a8c3df632735"
is_byok
false
latency
173
model_permaslug
"openai/gpt-oss-120b"
provider_name
"WandB"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777045941-rNSoY7PzJuB2Zp3m8UwY"
session_id
(null)
api_type
"completions"
id
"gen-1777045941-RYiaTyZYUqJkhfw0Tsp1"
upstream_id
"chatcmpl-bd02a8c3df632735"
total_cost
0.00310515
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
94.28%
Dialogue to Total Word Ratio
Ratio: 85.07%, Deviation: 4.93%
neededClean
false
wordsTotal
201
wordsDialogue
171
97.1418%