Barsukas
View
Words
Sentences
Conversations
Word Categories
Pending Imports
Dictionary
Tools
Batch Jobs
Logs
Operation Logs
Settings
Benchmarks
Dashboard
Benchmarks
Models
Recent Runs
linguistics.sqlite
Benchmarks
Antonym Identification
Run
Run Benchmark
Antonym Identification
Select Model
Model
-- Select a model --
Claude Haiku 4.5
Claude Opus 4.6
Claude Sonnet 4.6
Gemma 2 2B (LMStudio) - 1500 MB
Gemma 2 9B (LMStudio) - 5800 MB
Gemma 2B (LMStudio) - 1500 MB
Gemma 3 12B (LMStudio) - 8100 MB
GPT-5 mini
GPT-5 nano
GPT-5.2
Granite 3.2 8B (LMStudio) - 4900 MB
Llama 2 7B (LMStudio) - 4900 MB
Llama 3 8B (LMStudio) - 4900 MB
Llama 3.1 8B (LMStudio) - 4900 MB
Llama 3.2 1B (LMStudio) - 1300 MB
Ministral 8B (LMStudio) - 4900 MB
OLMo 3 7B (LMStudio) - 4300 MB
Phi-3.5 Mini (LMStudio) - 2500 MB
Phi-4 (LMStudio) - 9100 MB
Qwen2.5 7B (LMStudio) - 4300 MB
Qwen3 1.7B (LMStudio) - 1100 MB
Qwen3 4B (LMStudio) - 2800 MB
Qwen3 VL 8B (LMStudio) - 5000 MB
SmolLM2 1.7B (LMStudio) - 1100 MB
Select the model to run this benchmark against.
Benchmark execution is allowed only from direct local/private network IPs.
Start Benchmark Run
Cancel
Benchmark Info
A benchmark to evaluate a model's ability to identify the antonym of a word.