3 leaderboards. 54 contenders. Updated weekly from the original sources. Who's winning right now.
| 🥇 | claude-fable-5 Anthropic |
1510
|
| 🥈 | claude-opus-4-6-thinking Anthropic |
1504
|
| 🥉 | claude-opus-4-7-thinking Anthropic |
1502
|
| 4 | claude-opus-4-6 Anthropic |
1498
|
| 5 | claude-opus-4-7 Anthropic |
1492
|
| 6 | muse-spark Meta |
1487
|
| 7 | gemini-3.1-pro-preview Google |
1487
|
| 8 | gemini-3-pro Google |
1486
|
| 9 | claude-opus-4-8-thinking Anthropic |
1486
|
| 10 | gpt-5.5-high OpenAI |
1481
|
| 11 | gpt-5.4-high OpenAI |
1479
|
| 12 | claude-opus-4-8 Anthropic |
1477
|
| 13 | gemini-3.5-flash Google |
1477
|
| 14 | gpt-5.2-chat-latest-20260210 OpenAI |
1475
|
| 15 | glm-5.1 Z.ai |
1475
|
| 16 | qwen3.7-max-preview Alibaba |
1474
|
| 17 | grok-4.20-beta1 xAI |
1474
|
| 18 | gpt-5.5 OpenAI |
1474
|
| 19 | grok-4.20-beta-0309-reasoning xAI |
1474
|
| 20 | gemini-3-flash Google |
1473
|
| 🥇 | GPT-5.5 Thinking xHigh Effort OpenAI |
80.7
|
| 🥈 | GPT-5.4 Thinking xHigh Effort OpenAI |
80.3
|
| 🥉 | Gemini 3.1 Pro Preview High* Google |
79.9
|
| 4 | Claude Fable 5 Thinking xHigh Effort Anthropic |
78.3
|
| 5 | Claude 4.8 Opus Thinking xHigh Effort Anthropic |
77.2
|
| 6 | Claude 4.7 Opus Thinking xHigh Effort Anthropic |
76.9
|
| 7 | Claude 4.6 Opus Thinking High Effort Anthropic |
76.3
|
| 8 | Claude 4.5 Opus Thinking High Effort Anthropic |
76.0
|
| 9 | Claude 4.6 Sonnet Thinking Medium Effort Anthropic |
75.5
|
| 10 | Gemini 3.5 Flash High Google |
75.0
|
| 11 | GPT-5.2 High OpenAI |
74.8
|
| 12 | GPT-5.2 Codex OpenAI |
74.3
|
| 13 | Qwen 3.7 Max Alibaba |
74.3
|
| 14 | GPT-5.1 Codex Max High OpenAI |
74.0
|
| 15 | DeepSeek V4 Pro DeepSeek |
73.6
|
| 16 | Gemini 3 Pro Preview High Google |
73.4
|
| 17 | GPT-5.3 Codex High OpenAI |
72.8
|
| 18 | Gemini 3 Flash Preview High Google |
72.4
|
| 19 | Kimi K2.6 Thinking Moonshot AI |
72.2
|
| 20 | GPT-5.1 High OpenAI |
72.0
|
| 🥇 | Claude 4.5 Opus (high reasoning) Anthropic |
76.8
|
| 🥈 | Gemini 3 Flash (high reasoning) Google |
75.8
|
| 🥉 | 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) ZAI |
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) Kimi |
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
|
Sum of placement points across every tracked leaderboard. Rank 1 of a 20-model board scores 20; rank 20 scores 1. Higher = broader dominance.
Boards are updated weekly from each source. Cadences differ: Chatbot Arena updates hourly, LiveBench monthly, SWE-Bench Verified as new submissions are accepted. Scores are presented as published — no normalization across boards.