Live Leaderboards

trophyLeaderboard

3 leaderboards, 54 model rankings. Who's winning the AI race right now.

3

Benchmarks

54

Rankings

April 26, 2026

Last Scanned

emoji_events

Current Leaders

forum Chatbot Arena

🥇 claude-opus-4-7-thinking

Anthropic

1503

psychology LiveBench

🥇 GPT-5.5 Thinking xHigh Effort

OpenAI

80.71

code SWE-Bench Verified

🥇 Claude 4.5 Opus (high reasoning)

Anthropic

76.8

forum

Chatbot Arena

Elo ↗

Human preference rankings from blind A/B comparisons (5.7M+ votes)

#	Model	Elo
🥇 1	claude-opus-4-7-thinking Anthropic	1503
🥈 2	claude-opus-4-6-thinking Anthropic	1503
🥉 3	claude-opus-4-6 Anthropic	1496
4	claude-opus-4-7 Anthropic	1494
5	gemini-3.1-pro-preview Google	1493
6	muse-spark Meta	1492
7	gemini-3-pro Google	1486
8	grok-4.20-beta1 xAI	1482
9	gpt-5.4-high OpenAI	1481
10	grok-4.20-beta-0309-reasoning xAI	1479
11	gpt-5.2-chat-latest-20260210 OpenAI	1476
12	grok-4.20-multi-agent-beta-0309 xAI	1476
13	gemini-3-flash Google	1474
14	claude-opus-4-5-20251101-thinking-32k Anthropic	1473
15	glm-5.1 Z.ai	1470

psychology

LiveBench

Score ↗

Contamination-free benchmark with monthly-refreshed questions

#	Model	Score
🥇 1	GPT-5.5 Thinking xHigh Effort OpenAI	80.71
🥈 2	GPT-5.4 Thinking xHigh Effort OpenAI	80.28
🥉 3	Gemini 3.1 Pro Preview High* Google	79.93
4	Claude 4.7 Opus Thinking xHigh Effort Anthropic	76.91
5	Claude 4.6 Opus Thinking High Effort Anthropic	76.33
6	Claude 4.5 Opus Thinking High Effort Anthropic	75.96
7	Claude 4.6 Sonnet Thinking Medium Effort Anthropic	75.47
8	GPT-5.2 High OpenAI	74.84
9	GPT-5.2 Codex OpenAI	74.3
10	GPT-5.1 Codex Max High OpenAI	73.98
11	Gemini 3 Pro Preview High Google	73.39
12	GPT-5.3 Codex High OpenAI	72.76
13	Gemini 3 Flash Preview High Google	72.4
14	Kimi K2.6 Thinking Moonshot AI	72.17
15	GPT-5.1 High OpenAI	72.04

code

SWE-Bench Verified

Score ↗

Real-world software engineering task completion

#	Model	Score
🥇 1	Claude 4.5 Opus (high reasoning) Anthropic	76.8
🥈 2	Gemini 3 Flash (high reasoning) Google	75.8
🥉 3	MiniMax M2.5 (high reasoning) Minimax	75.8
4	Claude Opus 4.6 Anthropic	75.6
5	GPT-5-2 Codex OpenAI	72.8
6	GLM-5 (high reasoning) Z-AI	72.8
7	GPT-5-2 (high reasoning) OpenAI	72.8
8	GPT 5.2 Codex OpenAI	72.8
9	Claude 4.5 Sonnet (high reasoning) Anthropic	71.4
10	Kimi K2.5 (high reasoning) KimiAI	70.8
11	DeepSeek V3.2 (high reasoning) DeepSeek	70
12	Gemini 3 Pro Google	69.6
13	Claude 4.5 Haiku (high reasoning) Anthropic	66.6
14	GPT-5 Mini OpenAI	56.2

Like what you see?

Get tomorrow's brief delivered to your inbox.

One email per day. Unsubscribe anytime.