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。 並び替え: 正解テスト ↓.
| 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） |
|---|---|---|---|---|---|---|
| #15 | GPT-5.3-Codex medium | OpenAI | 4 | 8.4 | 15/21 | 16.2s |
| #17 | GLM 5 medium | Z.ai | 3 | 8.3 | 15/21 | 33.5s |
| #18 | Qwen3.7 Plus medium | Qwen | 5 | 8.2 | 15/21 | 38.9s |
| #20 | Gemini 3.5 Flash none | 3 | 8.1 | 15/21 | 9.93s | |
| #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 |
| #23 | GLM 5 Turbo medium | Z.ai | 4 | 8.0 | 14/21 | 23.0s |
| #24 | GPT-5.2 Chat none | OpenAI | 6 | 7.9 | 14/21 | 7.13s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 4 | 7.9 | 14/21 | 73.8s |
| #26 | Qwen3.6 Plus medium | Qwen | 5 | 7.9 | 14/21 | 30.7s |
| #27 | Gemma 4 31B medium | 2 | 7.8 | 14/21 | 56.5s | |
| #28 | Gemini 2.5 Flash medium | 6 | 7.8 | 14/21 | 15.5s | |
| #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 |