NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAGWB3T74EVBHT8JQECCSJ
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.3s
Cost:
$0.001006
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
96.8248%
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
The van idled behind the bouncy castle warehouse, headlights off, engine purring like a nervous cat. Molly unrolled a blueprint across the dashboard, pinning the corners with a half-eaten sausage roll and a squeaky rubber duck. "Phase one, the back gate," she whispered. Bill squinted at the paper. Someone had drawn a unicorn over the loading dock. He decided not to ask. From inside the party hall came a shriek of birthday laughter, followed by the wheeze of a bouncy castle losing air. Both thieves flinched in unison. Bill adjusted his ski mask, which had clearly been purchased from a toy shop and had a tiny pompom on top. "Ready?" he asked. "Almost," Molly said, sliding a crayon behind her ear. "Nobody gets hurt. We take presents, not cake." "And the goody bags?" She gave him a look that could curdle milk. "Bill." He sighed and dragged a sack the size of a sofa from under his seat. Lollipops rattled inside like loose teeth. Tiptoeing toward the gate, they slipped past a sleeping clown, a bored dog in a party hat, and a seven-year-old guarding a piƱata with a plastic sword.
created_at
"2026-10-08T08:36:49.132Z"
10/8/2026, 8:36:49 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10221
moderation_latency
(null)
generation_time
10221
tokens_prompt
75
tokens_completion
279
native_tokens_prompt
95
native_tokens_completion
1992
native_tokens_completion_images
(null)
native_tokens_reasoning
1570
native_tokens_cached
0
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
"end_turn"
service_tier
"default"
usage
0.0010055
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448609-xPtgUAnA5cQiSPqWa1Bv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448609-I306ReeWxSX7LJ6Xc9Pl"
upstream_id
"msg_011CfpTxPBrB7br35XGNETA6"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTxPBrB7br35XGNETA6"
is_byok
false
latency
1059
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0010055
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Claude Platform on AWS"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
100.00%
Dialogue to Total Word Ratio
Ratio: 10.31%, Deviation: 0.31%
neededClean
false
wordsTotal
194
wordsDialogue
20
96.8248%