排名 模型
🥇
claude-opus-4-7-thinking Anthropic · Proprietary
1581±0.0
🥈
claude-sonnet-4-6 Anthropic · Proprietary
1557±0.0
🥉
claude-opus-4-7 Anthropic · Proprietary
1556±0.0
4
claude-opus-4-6-thinking Anthropic · Proprietary
1538±0.0
5
gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary
1537±0.0
6
claude-opus-4-6 Anthropic · Proprietary
1534±0.0
7
gpt-5.5-high (codex-harness) OpenAI · Proprietary
1519±0.0
8
gemini-3.1-pro-preview Google · Proprietary
1490±0.0
9
gpt-5.5 (codex-harness) OpenAI · Proprietary
1489±0.0
10
qwen3.6-plus 阿里巴巴 · Proprietary
1467±0.0
11
gemini-3-pro Google · Proprietary
1453±0.0
12
gemini-3-flash Google · Proprietary
1447±0.0
13
gpt-5.3-codex (codex-harness) OpenAI · Proprietary
1441±0.0
14
gpt-5.4 OpenAI · Proprietary
1435±0.0
15
gemini-3-flash (thinking-minimal) Google · Proprietary
1421±0.0
16
gpt-5.1-high OpenAI · Proprietary
1421±0.0
17
grok-4.3 xAI · Proprietary
1396±0.0
18
gpt-5.1 OpenAI · Proprietary
1344±0.0
19
gemini-3.1-flash-lite-preview Google · Proprietary
1329±0.0
20
gemini-2.5-pro Google · Proprietary
1276±0.0

没有找到相关模型