資料取得日455 モデル · 53 開発元
455 モデル
| 順位 | モデル | 純改善 | タスク費用 P50 | 評価日 |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (High) | 14.33% ±2.18% | $1.64 | 2026-10-08 |
| 2 | GPT 6 Astra (Max) | 13.09% ±2.37% | $3.42 | 2026-10-08 |
| 3 | Claude Fable 5.1 (Max) | 12.66% ±2.05% | $6.35 | 2026-10-08 |
| 4 | Claude Sonnet 5.5 (Max) | 11.95% ±3.31% | $2.99 | 2026-10-08 |
| 5 | GPT 6.1 Sol (Max) | 11.72% ±3.05% | $0.57 | 2026-10-08 |
| 6 | GPT 6 Sol (Max) | 9.92% ±2.38% | $0.85 | 2026-10-08 |
| 7 | Gemini 4 Argon (High) | 9.26% ±2.36% | $0.66 | 2026-10-08 |
| 8 | Claude Fable 5 (High) | 8.94% ±1.27% | $2.6 | 2026-10-08 |
| 9 | Claude Opus 5 (Max) | 8.12% ±1.47% | $5.11 | 2026-10-08 |
| 10 | Claude Opus 5 (High) | 7.95% ±1.39% | $2.95 | 2026-10-08 |
| 11 | Claude Opus 4.8 (High) | 7.13% ±1.37% | $1.35 | 2026-10-08 |
| 12 | GPT 5.6 Sol (xHigh) | 6.23% ±1.28% | $1.26 | 2026-10-08 |
| 13 | Claude Sonnet 5 (High) | 4.91% ±1.69% | $0.98 | 2026-10-08 |
| 14 | GPT 5.5 (xHigh) | 4.38% ±1.09% | $1.15 | 2026-10-08 |
| 15 | Muse Spark 1.3 (Max) | 4.04% ±0.66% | $0.51 | 2026-10-08 |
| 16 | Deepseek V4.1 Flash (Max) | 3.8% ±0.39% | $0.12 | 2026-10-08 |
| 17 | Kimi K3 (Max) | 3.78% ±0.59% | $0.87 | 2026-10-08 |
| 18 | Hy4 preview | 3.61% ±0.7% | $0.34 | 2026-10-08 |
| 19 | MiMo V2.6 Pro | 3.52% ±1.92% | $0.1 | 2026-10-08 |
| 20 | GLM 5.2 (Max) | 3.19% ±0.73% | $0.81 | 2026-10-08 |
| 21 | Grok 4.7 (xHigh) | 2.83% ±1.71% | $1.81 | 2026-10-08 |
| 22 | Gemini 3.8 Flash (High) | 2.75% ±0.93% | $0.59 | 2026-10-08 |
| 23 | Qwen3.8 Max | 2.35% ±0.59% | $0.53 | 2026-10-08 |
| 24 | GLM 5.3 (Max) | 2.15% ±0.72% | $0.76 | 2026-10-08 |
| 25 | GPT 6 Luna (Max) | 1.93% ±0.64% | $0.07 | 2026-10-08 |
| 26 | DeepSeek V4 Pro (High) (0813) | 1.34% ±1.66% | — | 2026-10-08 |
| 27 | Grok 4.5 | 1.19% ±1.02% | $0.42 | 2026-10-08 |
| 28 | GPT 5.4 (High) | 1.19% ±0.96% | $0.55 | 2026-10-08 |
| 29 | Grok 4.6 (xHigh) | 1.05% ±1% | $1.19 | 2026-10-08 |
| 30 | GPT 5.5 | 0.93% ±1.01% | $0.6 | 2026-10-08 |
| 31 | GPT 5.6 Terra (xHigh) | 0.88% ±1.2% | $0.45 | 2026-10-08 |
| 32 | MiMo V2.6 Flash | 0.35% ±1.47% | $0.05 | 2026-10-08 |
| 33 | Step 5 Preview | 0.01% ±1.57% | $0.32 | 2026-10-08 |
| 34 | Qwen3.8 Flash Next | -0.72% ±0.62% | $0.17 | 2026-10-08 |
| 35 | GLM 5.3 Flash | -0.97% ±0.53% | $0.11 | 2026-10-08 |
| 36 | GPT 5.6 Luna (xHigh) | -1.48% ±0.69% | $0.07 | 2026-10-08 |
| 37 | Qwen 3.8 27B | -2.01% ±0.63% | $0.36 | 2026-10-08 |
| 38 | Gemini 3.7 Flash (High) | -2.1% ±0.79% | $0.46 | 2026-10-08 |
| 39 | Muse Spark 1.2 (xHigh) | -3.65% ±0.71% | $0.4 | 2026-10-08 |
| 40 | Muse Spark 1.1 | -5% ±0.51% | $0.48 | 2026-10-08 |
| 41 | Hy3 | -5.06% ±1.23% | $0.06 | 2026-10-08 |
| 42 | Qwen3.7 Max | -5.5% ±0.96% | $0.24 | 2026-10-08 |
| 43 | mistral-large-4 | -6.56% ±2.95% | $0.92 | 2026-10-08 |
| 44 | Minimax M3 | -6.95% ±0.9% | $0.09 | 2026-10-08 |
| 45 | Qwen3.7 Plus | -7.21% ±1.45% | $0.11 | 2026-10-08 |
| 46 | Mimo V2.5 Pro | -7.78% ±0.9% | $0.05 | 2026-10-08 |
| 47 | Gemini 3.6 Flash (High) | -7.79% ±1.06% | $0.25 | 2026-10-08 |
| 48 | Gemini 3.1 Pro Preview | -7.79% ±1% | $0.31 | 2026-10-08 |
| 49 | Inkling Small | -10.32% ±1.44% | $0.14 | 2026-10-08 |
| 50 | Inkling | -11.51% ±1.12% | $0.34 | 2026-10-08 |
| 51 | Mistral Medium 3.5 | -12.6% ±1.45% | $0.75 | 2026-10-08 |
| 52 | Solar Pro 4 | -16.98% ±1.86% | $0.04 | 2026-10-08 |