NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBNA4E6VQYVVP5M5X8KZ05
Run Details
Model:
Ember-1 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 11s
Cost:
$0.070772
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
6.35%
Dialogue to Total Word Ratio
(details)
53.1745%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 unrolled the blueprints across the hood of Bill's borrowed hatchback, weighing down the corners with juice boxes and a wounded-looking piƱata. She stabbed a finger at the crayon diagram, which featured stick figures, a dragon that might have been a dog, and a large X over the gift table. "The bouncy castle is our exit." Bill squinted. He trusted Molly's plans the way he trusted gas station sushi: completely, and against all evidence. "What's the code?" Bill asked. "Stop, drop, and roll." "That's for fires." Molly had spent three weeks casing the Hendersons' backyard disguised as a clown, which backfired when the children found her funnier than the real clown and demanded she perform at the party itself. Now she had a legitimate invitation, a balloon animal alibi, and a unicycle getaway if things went sideways. Bill's job was the loot sack. He had practiced by robbing his own pantry and been bitten by the cat only twice, which he counted as a personal best. If they got caught, the fallback plan was simple: blend in with the guests. "Act seven years old," Molly said. Bill nodded solemnly. He had been preparing for that role his entire adult life.
created_at
"2026-10-13T10:06:50.519Z"
10/13/2026, 10:06:50 AM
model
"fireworks/ember-1-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
578
moderation_latency
(null)
generation_time
70537
tokens_prompt
75
tokens_completion
3952
native_tokens_prompt
149
native_tokens_completion
4715
native_tokens_completion_images
(null)
native_tokens_reasoning
3952
native_tokens_cached
148
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
0.0707724
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791886010-kA6AbHFsixXJs7PHJ4AR"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791886010-sUaNEzp4eUV47M8BodY7"
upstream_id
"chatcmpl-bb8b986163b4465a999c78ac48554874"
provider_responses
0
endpoint_id
"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id
"chatcmpl-bb8b986163b4465a999c78ac48554874"
is_byok
false
latency
578
model_permaslug
"fireworks/ember-1-20260923"
provider_name
"Fireworks"
status
200
total_cost
0.0707724
cache_discount
0.0003996
upstream_inference_cost
0
provider_name
"Fireworks"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
6.35%
Dialogue to Total Word Ratio
Ratio: 22.89%, Deviation: 12.89%
neededClean
false
wordsTotal
201
wordsDialogue
46
53.1745%