Arena 基准测试
Compare top models across the benchmark suite that best represents arena performance. Use this page as the fastest way to inspect the relevant tests, then jump into the full matrix when you want broader context.
2
类别中的基准测试
135
有覆盖的模型
0
有人类基准的基准测试
0
饱和的基准测试
包含内容
The current benchmark set in this category, with context on what each test captures.
LMSYS Chatbot Arena Elo Rating
The most trusted 'vibes-based' benchmark — reflects real human preferences, not just academic metrics. Widely considered the most meaningful overall ranking.
LiveBench (Dynamic)
Contamination-free by design — uses new questions regularly. Top models still score below 70%, making it highly discriminating.
LMSYS Chatbot Arena Elo Rating
Human preference rating from 6M+ crowdsourced blind head-to-head comparisons. Users chat with two anonymous models and pick the better response.
Why it matters
The most trusted 'vibes-based' benchmark — reflects real human preferences, not just academic metrics. Widely considered the most meaningful overall ranking.
Arena Elo Scores (129 models)
How to Read This Page
Performance Tiers
Model Types
Saturated benchmarks have top models clustered above 90%, making them less useful for comparison.
Scores sourced from official model cards, technical reports, and third-party evaluations (Artificial Analysis, LMSYS Arena). Last updated: 2026-09-22T18:30:19.136Z. Some scores are approximate.
AI benchmarks are grouped into categories like coding, math, reasoning, knowledge, and safety. Each category contains multiple standardized tests that measure specific aspects of model performance. This page focuses on one category so you can compare models within a specific skill area.
Each benchmark has its own scoring method - accuracy percentage, pass rate, Elo rating, or normalized score. We display raw scores from official evaluations and community-run tests. Scores are updated hourly as new evaluation results become available.
A saturated benchmark is one where top models score near the maximum (typically above 95%). This means the benchmark no longer effectively differentiates between the best models, and newer, harder benchmarks are needed to measure progress.