Knowledge & language Text Model Rankings
Factual accuracy, long-context understanding, language, instruction following, and false-premise detection.
| 1 | 82.0 | 60.03 | 1M | $8/M | $40/M | $0.2/M | 2026-11-09 | ||
| 2 | 72.2 | 55.64 | 1.1M | $10/M | $50/M | 2026-09-03 | |||
| 3 | 70.7 | 66.07 | 1.1M | $2/M | $10/M | 2026-10-08 | |||
| 4 | 67.8 | 69.17 | 1M | $4/M | $20/M | $0.2/M | 2026-09-22 | ||
| 5 | 66.4 | 51.81 | 1M | $10/M | $50/M | $0.25/M | 2026-09-01 | ||
| 6 | 65.1 | 64.84 | 1M | $2/M | $10/M | $0.1/M | 2026-09-28 | ||
| 7 | 64.7 | 53.34 | 1.1M | - | - | - | 2026-07-09 | ||
| 8 | 64.5 | 61.05 | 1.1M | $1/M | $5/M | 2026-10-26 | |||
| 9 | 64.4 | 53.75 | 1M | - | 2026-08-03 | ||||
| 10 | 64.2 | 54.48 | 1.1M | $2/M | $10/M | 2026-09-22 | |||
| 11 | 63.9 | 59.8 | 1M | - | 2026-09-30 | ||||
| 12 | 63.3 | 51.81 | 1M | $5/M | $25/M | $0.5/M | 2026-05-28 | ||
| 13 | 62.8 | 45.95 | 1.1M | $5/M | $30/M | 2026-04-23 | |||
| 14 | 62.4 | 44.05 | 1M | $10/M | $50/M | $1/M | 2026-06-09 | ||
| 15 | 61.5 | 53.33 | 1M | $5/M | $25/M | $0.5/M | 2026-07-24 | ||
| 16 | 61.0 | 62.65 | 1M | - | 2026-09-02 | ||||
| 17 | 60.7 | 58.62 | 500K | - | 2026-09-21 | ||||
| 18 | 58.9 | 40.02 | 1M | - | 2026-05-21 | ||||
| 19 | 58.9 | 68.66 | 1M | - | 2026-09-20 | ||||
| 20 | 58.8 | 61.26 | 1M | $3/M | $15/M | - | 2026-07-16 | ||
| 21 | 58.7 | 48.86 | 500K | - | 2026-08-12 | ||||
| 22 | 57.9 | 49.1 | 1M | $1.25/M | $4.25/M | $0.15/M | 2026-09-02 | ||
| 23 | 57.2 | 64.94 | 1M | - | 2026-10-07 | ||||
| 24 | 56.7 | 79.31 | 1M | - | 2026-09-10 |
Page 1 of 3
Efficiency Frontier
The line shows the best score available at each budget. Models below it have a higher-scoring alternative within the same budget.
Price weighted: cache 7 · input 2 · output 1 (per million tokens)
















































