排名 模型 得分
🥇
gpt-5.4-medium (codex-harness) OpenAI · Proprietary
1469±43.0 5 - 32 192 $2.50 / $15 1.1M 1468.678 [1425.6, 1511.7] 482.31 · 不稳 Proprietary
🥈
gpt-5.4-high (codex-harness) OpenAI · Proprietary
1461±47.9 11 - 25 164 $2.50 / $15 1.1M 1460.921 [1413.0, 1508.8] 597.72 · 不稳 Proprietary
🥉
gpt-5.3-codex (codex-harness) OpenAI · Proprietary
1424±31.2 10 - 18 373 $1.75 / $14 400K 1424.409 [1393.2, 1455.6] 253.32 · 不稳 Proprietary
4
23
gpt-5.2 OpenAI · Proprietary
1406±16.1 4 - 76 1.6K $1.75 / $14 400K 1405.643 [1389.6, 1421.7] 67.34 · 不稳 Proprietary
5
gpt-5-medium OpenAI · Proprietary
1400±12.8 27 - 46 3.8K $1.25 / $10 400K 1400.029 [1387.2, 1412.8] 42.54 · 不稳 Proprietary
6
gpt-5.1-medium OpenAI · Proprietary
1396±9.7 27 - 46 6.3K $1.25 / $10 400K 1396.375 [1386.7, 1406.0] 24.31 · 不稳 Proprietary
7
21
gpt-5.1 OpenAI · Proprietary
1360±8.7 4 - 68 10.4K $1.25 / $10 400K 1359.951 [1351.3, 1368.6] 19.51 · 不稳 Proprietary
8
gpt-5.2-codex OpenAI · Proprietary
1342±12.0 46 - 52 3.2K $1.75 / $14 400K 1342.335 [1330.3, 1354.3] 37.57 · 不稳 Proprietary
9
gpt-5.1-codex OpenAI · Proprietary
1335±9.7 48 - 58 6.4K $1.25 / $10 400K 1335.028 [1325.3, 1344.8] 24.61 · 不稳 Proprietary
10
gpt-5.1-codex-mini OpenAI · Proprietary
1250±17.3 63 - 71 1.5K $0.25 / $2 400K 1250.410 [1233.1, 1267.7] 77.78 · 不稳 Proprietary

没有找到相关模型