模型排行
1190 个模型 · 5 个榜单 · 2 个数据来源
网页王座
开源之光
国产之光
最多人测
这一期的变化
gpt-5.5-high (codex-harness)编程榜 · 第 7新上榜
Grok 4.3智力榜 · 第 8新上榜
mimo-v2.5-pro编程榜 · 第 9新上榜
DeepSeek V4 Pro (Reasoning, Max Effort)智力榜 · 第 13新上榜
gpt-5.5 (codex-harness)编程榜 · 第 15新上榜
| 排名 | 变化 | 模型 | 得分 | 置信区间 | 投票 | 价格 $/M |
|---|---|---|---|---|---|---|
| 1 | — | claude-opus-4-7-thinking闭源Anthropic · 另有 1 个档位 | 1,571 | ±13 | 2,490 | — |
| 2 | — | claude-opus-4-6-thinking闭源Anthropic · 另有 1 个档位 | 1,548 | ±9 | 5,750 | — |
| 3 | — | glm-5.1开源Z.ai | 1,534 | ±11 | 3,412 | — |
| 4 | ▲ 1 | claude-sonnet-4-6闭源Anthropic | 1,527 | ±8 | 8,709 | — |
| 5 | ▼ 1 | kimi-k2.6开源Moonshot AI | 1,526 | ±14 | 2,130 | — |
| 6 | — | muse-spark闭源Meta | 1,509 | ±16 | 1,635 | — |
| 7 | 新 | gpt-5.5-high (codex-harness)闭源OpenAI | 1,492 | ±14 | 2,126 | — |
| 8 | ▼ 1 | claude-opus-4-5-20251101-thinking-32k闭源Anthropic | 1,491 | ±7 | 13,065 | — |
| 9 | 新 | mimo-v2.5-pro开源Xiaomi | 1,475 | ±12 | 2,681 | — |
| 10 | ▼ 2 | qwen3.6-plus闭源Alibaba | 1,467 | ±11 | 3,716 | — |
| 11 | ▼ 2 | claude-opus-4-5-20251101闭源Anthropic | 1,467 | ±6 | 15,309 | — |
| 12 | ▼ 1 | gpt-5.4-high (codex-harness)闭源OpenAI | 1,457 | ±17 | 1,482 | — |
| 13 | ▼ 1 | deepseek-v4-pro-thinking开源DeepSeek | 1,455 | ±16 | 1,469 | — |
| 14 | ▼ 4 | gemini-3.1-pro-preview闭源Google | 1,453 | ±8 | 7,813 | — |
| 15 | 新 | gpt-5.5 (codex-harness)闭源OpenAI | 1,447 | ±14 | 1,879 | — |
| 16 | 新 | mimo-v2.5开源Xiaomi | 1,444 | ±15 | 1,570 | — |
| 17 | ▼ 4 | glm-4.7开源Z.ai | 1,440 | ±10 | 4,883 | — |
| 18 | ▼ 4 | gemini-3-pro闭源Google | 1,438 | ±7 | 17,173 | — |
| 19 | ▼ 2 | glm-5开源Z.ai | 1,437 | ±8 | 6,393 | — |
| 20 | ▼ 5 | gpt-5.4-medium (codex-harness)闭源OpenAI | 1,437 | ±16 | 1,448 | — |
| 21 | ▼ 5 | gemini-3-flash闭源Google · 另有 1 个档位 | 1,437 | ±7 | 13,282 | — |
| 22 | ▼ 4 | kimi-k2.5-thinking开源Moonshot AI | 1,430 | ±7 | 8,721 | — |
| 23 | ▼ 4 | mimo-v2-pro闭源Xiaomi | 1,430 | ±9 | 4,869 | — |
| 24 | ▼ 4 | minimax-m2.7开源MiniMax | 1,411 | ±10 | 4,502 | — |
| 25 | 新 | grok-4.3闭源xAI | 1,408 | ±18 | 1,048 | — |
| 26 | ▼ 5 | kimi-k2.5-instant开源Moonshot AI | 1,408 | ±11 | 3,609 | — |
| 27 | ▼ 5 | gpt-5.3-codex (codex-harness)闭源OpenAI | 1,407 | ±12 | 2,965 | — |
| 28 | ▼ 5 | gpt-5.2闭源OpenAI | 1,404 | ±17 | 1,459 | — |
| 29 | ▼ 4 | gpt-5.4-mini-high闭源OpenAI | 1,400 | ±11 | 3,410 | — |
| 30 | ▼ 6 | grok-4.20-beta-0309-reasoning闭源xAI | 1,399 | ±9 | 5,083 | — |
| 31 | ▼ 5 | gpt-5-medium闭源OpenAI | 1,393 | ±13 | 3,755 | — |
| 32 | ▼ 5 | minimax-m2.1-preview开源MiniMax | 1,392 | ±8 | 9,279 | — |
| 33 | ▼ 5 | gpt-5.1-medium闭源OpenAI | 1,391 | ±9 | 6,124 | — |
| 34 | ▼ 4 | claude-sonnet-4-5-20250929-thinking-32k闭源Anthropic | 1,388 | ±7 | 15,741 | — |
| 35 | ▼ 6 | qwen3.5-397b-a17b开源Alibaba | 1,387 | ±8 | 7,601 | — |
| 36 | ▼ 5 | claude-sonnet-4-5-20250929闭源Anthropic | 1,386 | ±6 | 18,409 | — |
| 37 | ▼ 5 | claude-opus-4-1-20250805闭源Anthropic | 1,385 | ±9 | 8,572 | — |
| 38 | ▼ 5 | minimax-m2.5开源MiniMax | 1,383 | ±8 | 7,857 | — |
| 39 | ▼ 5 | deepseek-v3.2-thinking开源DeepSeek · 另有 1 个档位 | 1,368 | ±8 | 7,918 | — |
| 40 | ▼ 5 | qwen3.5-122b-a10b开源Alibaba | 1,363 | ±8 | 6,318 | — |
| 41 | ▼ 5 | glm-4.6开源Z.ai | 1,355 | ±9 | 8,354 | — |
| 42 | ▼ 5 | qwen3.5-27b开源Alibaba | 1,350 | ±9 | 5,905 | — |
| 43 | ▼ 5 | gpt-5.1闭源OpenAI | 1,339 | ±7 | 12,871 | — |
| 44 | ▼ 5 | mimo-v2-flash (non-thinking)开源Xiaomi · 另有 1 个档位 | 1,337 | ±8 | 6,734 | — |
| 45 | ▼ 5 | gpt-5.2-codex闭源OpenAI | 1,335 | ±8 | 7,761 | — |
| 46 | ▼ 5 | kimi-k2-thinking-turbo开源Moonshot AI | 1,330 | ±6 | 15,371 | — |
| 47 | ▼ 5 | gpt-5.1-codex闭源OpenAI | 1,329 | ±10 | 6,229 | — |
| 48 | ▼ 5 | claude-haiku-4-5-20251001闭源Anthropic | 1,317 | ±6 | 18,685 | $2.0 |
| 49 | ▼ 5 | minimax-m2开源MiniMax | 1,304 | ±9 | 8,403 | — |
| 50 | ▼ 5 | deepseek-v3.2-exp开源DeepSeek | 1,286 | ±11 | 4,871 | — |
智力进步
涨得最多 · Anthropic +57.2目前最高 · Anthropic 64.6最高与最低相差 18.1 分时间范围 2025年11月 – 2026年11月
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi