資料取得日455 モデル · 53 開発元
455 モデル
| 順位 | モデル | 解決率 | タスク単価 | モデル公開日 |
|---|---|---|---|---|
| 1 | Opus 5.5 · Claude Code (max) | 64.85% ±3.11% | $14.299 | 2026-09-22 |
| 2 | Sonnet 5.5 · Claude Code (max) | 61.82% ±2.94% | $22.223 | 2026-09-28 |
| 3 | GPT-6 Astra · Codex (max) | 58.18% ±2.79% | $9.901 | 2026-09-03 |
| 3 | GPT-6.1 Sol · Codex (max) | 58.18% ±3.11% | $1.922 | 2026-09-29 |
| 5 | Fable 5.1 · Claude Code (max) | 57.88% ±3.76% | $18.92 | 2026-09-01 |
| 5 | Fable 5.1 · Claude Code (xhigh) | 57.88% ±3.36% | $14.764 | 2026-09-01 |
| 5 | GPT-6 Astra · Codex (high) | 57.88% ±2.97% | $6.877 | 2026-09-03 |
| 5 | GPT-6 Astra · Codex (xhigh) | 57.88% ±2.72% | $7.123 | 2026-09-03 |
| 9 | Fable 5.1 · Claude Code (high) | 54.55% ±3.44% | $12.077 | 2026-09-01 |
| 10 | GPT-6 Astra · Codex (medium) | 54.24% ±2.66% | $5.802 | 2026-09-03 |
| 11 | Fable 5.1 · Claude Code (medium) | 53.94% ±3.39% | $8.585 | 2026-09-01 |
| 11 | Opus 5 · Claude Code (xhigh) | 53.94% ±3.17% | $18.443 | 2026-07-24 |
| 13 | Opus 5 · Claude Code (max) | 51.82% ±3.39% | $18.088 | 2026-07-24 |
| 14 | GPT-6 Astra · Codex (low) | 50.61% ±2.75% | $4.719 | 2026-09-03 |
| 15 | Opus 5 · Claude Code (high) | 50.3% ±3.73% | $14.128 | 2026-07-24 |
| 16 | GPT-6 Sol · Codex (max) | 49.39% ±3.23% | $4.398 | 2026-09-22 |
| 17 | Opus 5 · Claude Code (medium) | 44.85% ±3.83% | $9.671 | 2026-07-24 |
| 18 | Fable 5 · Claude Code (max) | 44.55% ±3.85% | $22.015 | 2026-06-09 |
| 19 | Fable 5.1 · Claude Code (low) | 43.33% ±3.61% | $7.148 | 2026-09-01 |
| 20 | GLM-5.3 · Claude Code (max) | 41.82% ±3.23% | $8.266 | 2026-08-14 |
| 21 | Grok 4.7 · Grok Build (xhigh) | 37.58% ±3.54% | $11.161 | 2026-09-21 |
| 22 | GPT-5.6 Sol · Codex (max) | 37.27% ±3.78% | $7.702 | 2026-06-26 |
| 23 | GLM-5.3-Flash · Claude Code (none) | 35.76% ±3.54% | $8.737 | 2026-08-26 |
| 24 | Opus 5 · Claude Code (low) | 34.85% ±3.94% | $7.254 | 2026-07-24 |
| 25 | Qwen3.8-Max-0902 · Claude Code (max) | 26.97% ±3.78% | $14.047 | 2026-09-02 |
| 26 | Opus 4.8 · Claude Code (max) | 23.64% ±3.56% | $19.64 | 2026-05-28 |
| 27 | GPT-5.6 Terra · Codex (max) | 21.52% ±3.25% | $5.253 | 2026-06-26 |
| 28 | Grok 4.6 · Grok Build (high) | 20.3% ±3.09% | $10.884 | 2026-08-12 |
| 29 | Gemini 3.8 Flash · mini-SWE-agent (high) | 19.09% ±3.36% | $5.542 | 2026-09-02 |
| 30 | GPT-5.6 Luna · Codex (max) | 17.27% ±2.85% | $1.051 | 2026-06-26 |
| 31 | GPT-6 Luna · Codex (max) | 16.36% ±2.72% | $0.219 | 2026-09-22 |
| 32 | Muse Spark 1.3 · Muse Code (xhigh) | 14.55% ±2.94% | $0 | 2026-09-02 |
| 33 | Grok 4.5 · Grok Build (high) | 12.42% ±2.62% | $6.346 | 2026-07-16 |
| 33 | Sonnet 5 · Claude Code (max) | 12.42% ±3.06% | $29.103 | 2026-06-30 |
| 35 | Gemini 3.7 Flash · mini-SWE-agent (high) | 11.21% ±2.45% | $3.824 | 2026-08-13 |