whereismyai
LiveBench
LiveBench is an objective benchmark platform that evaluates large language models across multiple tasks.
LiveBench provides an objective benchmark for evaluating large language models using tasks refreshed every six months. It includes objective tasks across seven categories to test capabilities like reasoning, coding, mathematics, and instruction following. Users can view rankings, sort scores down to subtasks, and analyze costs per successful task for each model. The platform allows comparisons across open weights and proprietary models from various organizations. It offers analytical views such as quality versus cost charts and category profiles to help assess model efficiency.
LiveBench at a glance
- Best for: Software engineer, Researcher
- Runs on: Web
- Pricing: Free
- Released: June 2024
- Category: AI research tool
- Website: livebench.ai
Key features
- Compare leaderboard scores across multiple categories
- Analyze cost per successful task for models
- View subtask performance by clicking rows
- Filter models by open weights or organizations
- Inspect quality versus cost charts
- Compare category profiles across selected models
Use it for
- Compare large language model performance
- Analyze running costs of AI models
- Evaluate model capabilities in reasoning and coding
- Research contamination-free benchmark results
Alternatives to LiveBench
- MTEB — Evaluates embedding models across over 1000 tasks and 1000 languages.
- LiveFrame — It provides verified runtime, control, and stability reports with digest-bound ledgers.
- Benchpress — Evaluates document artificial intelligence models against specific user pages for accuracy, cost, and speed.
- LLM Stats — Independent rankings updated continuously from live API metrics.
- Self Bench — Evaluates coding agents on internal repository tasks instead of generic public datasets.
- Fightbench — It tests artificial intelligence models on game memory rather than pixels.
- Overview — Learn language models by running hands-on experiments without writing scripts
- NanoJev — It runs parallel decisions and outputs probability distributions without output-token decoding.
- VLMEvalKit — Evaluate large vision-language models across numerous benchmarks with a single command.
- Laya — It runs typed decisions in a single forward pass over 100+ languages.
- DeepInfer Studio — Explore AI inference workflows and resource trade-offs without requiring expensive hardware or GPUs.
- Lighteval — Evaluates LLMs across multiple backends with thousands of built-in tasks.
All LiveBench alternatives