AI BENCHY 失敗分析
不正解 の失敗
どのAIモデルで 不正解 が起きやすいかを確認し、選ぶ前に信頼性のリスクを見極められます。
| 順位 | モデル | 企業 | 不正解 件数 | スコア | 正解テスト | 応答時間（平均） |
|---|---|---|---|---|---|---|
| #71 | Step 3.7 Flash high | Stepfun | 6 | 7.0 | 11/21 | 64.5s |
| #75 | Ring-2.6-1T medium | Inclusionai | 6 | 6.9 | 11/21 | 61.3s |
| #78 | Qwen3.6 27B medium | Qwen | 6 | 6.8 | 10/21 | 59.7s |
| #107 | Laguna Xs.2 medium | Poolside | 6 | 5.8 | 6/19 | 6.73s |
| #130 | MiniMax M2.7 medium | Minimax | 6 | 5.3 | 5/21 | 38.2s |
| #14 | Qwen3.6 Max Preview medium | Qwen | 5 | 8.5 | 16/21 | 59.6s |
| #16 | Gemini 3 Flash Preview low | 5 | 8.4 | 16/21 | 5.76s | |
| #18 | Qwen3.7 Plus medium | Qwen | 5 | 8.2 | 15/21 | 38.9s |
| #19 | Seed-2.0-Lite medium | Bytedance Seed | 5 | 8.2 | 14/21 | 47.1s |
| #21 | GPT-5.4 medium | OpenAI | 5 | 8.0 | 14/21 | 22.3s |
| #22 | Step 3.7 Flash medium | Stepfun | 5 | 8.0 | 14/21 | 20.4s |
| #26 | Qwen3.6 Plus medium | Qwen | 5 | 7.9 | 14/21 | 30.7s |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 5 | 7.8 | 14/21 | 42.5s |
| #32 | Gemini 3.5 Flash minimal | 5 | 7.7 | 14/21 | 1.57s | |
| #38 | Grok 4.3 medium | X AI | 5 | 7.6 | 13/21 | 47.5s |