Overview / Description
LM Market Cap is an AI model comparison platform that tracks 345 large language models across 57 providers, ranking them hourly by a composite score covering performance benchmarks, API pricing, speed, and specialized capabilities including coding, math, and reasoning.
Leaderboards cover models from OpenAI, Anthropic, Google, DeepSeek, Mistral, and others, with benchmark data from MMLU, GPQA, HumanEval, and SWE-bench. Separate rankings break down performance by task: coding (320 models tracked), math, reasoning, writing, instruction-following, and image and video generation.
Practical tools include a cost calculator, token counter, VRAM calculator, subscription calculator, and a watchlist for tracking API price changes across providers. API pricing is monitored live, making the platform useful for teams comparing cost-per-token before committing to a model.
All features are free to use without an account.
Best for: AI engineers, researchers, and product teams evaluating which LLM to use for a specific task — particularly for cost vs. performance trade-offs across the major API providers.
Used For
AI tool for fun workflows
Pricing
Pros & Cons
Pros
• Hourly-updated composite rankings across 345 models and 57 providers — fresher than static leaderboards • Specialized leaderboards for coding, math, reasoning, and writing give task-specific rankings beyond generic benchmarks • Built-in cost calculator and API price watchlist for tracking changes across OpenAI, Anthropic, Google, and others • VRAM and subscription calculators help teams compare on-premise vs. API cost before deploying
Cons
• Coverage depth varies by model — newer or smaller providers may have incomplete benchmark data • Composite scoring methodology is not fully documented — hard to audit how category weights are assigned • No live API testing or output quality comparison — rankings are benchmark-based only
Questions & Answers
Alternatives
Compare this tool against close alternatives in the same category, focusing on output quality, onboarding speed, and workflow fit.