Research

Chatbot Arena Elo Leaderboard June 2026

LMSYS Chatbot Arena Elo leaderboard for June 2026. GPT-5.6, Claude Opus 4.7, Gemini 3.2 Pro, and Claude Mythos 5 lead the frontier; DeepSeek V4.1 sits in the top open-weight slot.

By Ramanath, CTO & Co-Founder at Presenc AI · Last updated: June 2026

The LMSYS Chatbot Arena Elo leaderboard is the most widely cited blind-A/B evaluation of frontier LLMs. This page snapshots the public leaderboard as of June 2026 across the headline categories.

Arena Hard Top 15 (June 2026)

RankModelVendorElo
1GPT-5.6 ProOpenAI~1465
2Claude Mythos 5Anthropic~1458
3Claude Opus 4.7Anthropic~1452
4Gemini 3.2 ProGoogle~1448
5GPT-5.6OpenAI~1440
6Claude Sonnet 4.6Anthropic~1428
7Gemini 3.2 FlashGoogle~1418
8DeepSeek V4.1 ProDeepSeek~1410
9Qwen 3.7Alibaba~1400
10GPT-5.6 miniOpenAI~1392
11Grok 4xAI~1385
12Llama 4.5 MaverickMeta~1370
13GLM-6Zhipu AI~1360
14Mistral Large 3Mistral AI~1352
15Kimi K2.6Moonshot AI~1345

Key Takeaways

  • GPT-5.6 Pro overtook Claude Mythos 5 in Arena Elo within two weeks of release.
  • The top eight models are clustered within ~55 Elo points, the tightest spread on record.
  • DeepSeek V4.1 Pro is the highest open-weight entry, within ~55 points of the top closed model.
  • Specialized variants (Pro, Mythos) outscore base variants by 6 to 15 Elo on Arena Hard but the gap is narrower on default Arena.

Methodology

Scores from lmarena.ai public leaderboard; Arena Hard is the more discriminating variant used here. Elo numbers are approximate and shift daily as new votes accumulate. Updated monthly.

How Presenc AI Helps

Presenc AI tracks brand visibility on the top-Elo models continuously so brand teams see citation patterns shift in step with frontier-model competitive dynamics.

Frequently Asked Questions

A blind A/B ranking system where users vote on which of two anonymous model responses is better. Elo scores update continuously as votes accumulate.
Arena Hard is a curated harder prompt subset that better discriminates between top-tier models. Score spreads are wider on Arena Hard than on the default mixed-difficulty Arena.
GPT-5.6 Pro from OpenAI at approximately 1465, narrowly ahead of Claude Mythos 5 at approximately 1458.
Top-of-leaderboard positions typically hold for four to six weeks before a competitor release reshuffles the top spots.

Track Your AI Visibility

See how your brand appears across ChatGPT, Claude, Perplexity, and other AI platforms. Start monitoring today.