Knowledge & language Text Model Leaderboard
Factual accuracy, long-context understanding, language, instruction following, and false-premise detection.
| 1 | Nov 9, 2026 | 80%22 items | 82.0 | |
| 2 | Sep 3, 2026 | 100%27 items | 72.3 | |
| 3 | Oct 8, 2026 | 100%27 items | 70.7 | |
| 4 | Sep 22, 2026 | 100%27 items | 67.9 | |
| 5 | Sep 1, 2026 | 100%26 items | 66.4 | |
| 6 | Sep 28, 2026 | 100%27 items | 65.2 | |
| 7 | Jul 9, 2026 | 80%25 items | 64.7 | |
| 8 | Oct 26, 2026 | 80%18 items | 64.5 | |
| 9 | Aug 3, 2026 | 80%23 items | 64.4 | |
| 10 | Sep 22, 2026 | 100%25 items | 64.2 | |
| 11 | Sep 30, 2026 | 100%27 items | 64.0 | |
| 12 | May 28, 2026 | 80%22 items | 63.4 | |
| 13 | OPGPT-5.5 | Apr 23, 2026 | 80%20 items | 62.9 |
| 14 | Jun 9, 2026 | 80%22 items | 62.4 | |
| 15 | Jul 24, 2026 | 100%26 items | 61.5 | |
| 16 | Sep 2, 2026 | 80%26 items | 61.0 | |
| 17 | XAGrok 4.7 | Sep 21, 2026 | 80%26 items | 60.7 |
| 18 | May 21, 2026 | 80%17 items | 59.0 | |
| 19 | Sep 20, 2026 | 60%19 items | 58.9 | |
| 20 | MAKimi K3 | Jul 16, 2026 | 100%26 items | 58.8 |
| 21 | XAGrok 4.6 | Aug 12, 2026 | 100%26 items | 58.8 |
| 22 | Sep 10, 2026 | 80%25 items | 58.4 | |
| 23 | Sep 2, 2026 | 60%24 items | 57.9 | |
| 24 | Oct 7, 2026 | 100%27 items | 57.2 | |
| 25 | Oct 17, 2026 | 80%21 items | 56.3 | |
| 26 | XAGrok 4.5 | Jul 8, 2026 | 80%20 items | 55.7 |
| 27 | ZAGLM 5.3 | Oct 5, 2026 | 100%27 items | 55.5 |
| 28 | Sep 22, 2026 | 100%27 items | 55.5 | |
| 29 | Jul 9, 2026 | 100%24 items | 55.4 | |
| 30 | Feb 17, 2026 | 80%19 items | 55.4 | |
| 31 | Jul 21, 2026 | 80%20 items | 54.9 | |
| 32 | Aug 5, 2026 | 80%18 items | 54.1 | |
| 33 | Jul 21, 2026 | 80%21 items | 54.1 | |
| 34 | Apr 8, 2026 | 60%16 items | 53.2 | |
| 35 | Jun 30, 2026 | 80%22 items | 53.1 | |
| 36 | Apr 22, 2026 | 60%15 items | 53.1 | |
| 37 | Apr 21, 2026 | 80%18 items | 52.8 | |
| 38 | Oct 19, 2026 | 60%15 items | 52.2 | |
| 39 | Sep 21, 2026 | 60%21 items | 52.0 | |
| 40 | Aug 13, 2026 | 80%23 items | 51.4 | |
| 41 | Apr 22, 2026 | 40%12 items | 51.4 | |
| 42 | XAGrok 4.3 | Apr 17, 2026 | 60%15 items | 51.2 |
| 43 | Aug 26, 2026 | 60%24 items | 51.2 | |
| 44 | Jun 1, 2026 | 80%21 items | 50.9 | |
| 45 | Jul 9, 2026 | 100%25 items | 50.7 | |
| 46 | Jun 12, 2026 | 60%15 items | 50.1 | |
| 47 | Jul 31, 2026 | 60%18 items | 49.8 | |
| 48 | Mar 17, 2026 | 80%20 items | 49.6 | |
| 49 | Jun 2, 2026 | 40%14 items | 49.5 | |
| 50 | ZAGLM-5.2 | Jun 13, 2026 | 100%20 items | 47.7 |
| 51 | TMInkling | Jul 15, 2026 | 80%23 items | 47.2 |
| 52 | Jul 23, 2026 | 40%11 items | 46.7 | |
| 53 | Oct 15, 2025 | 100%19 items | 46.6 | |
| 54 | ZAGLM-5.1 | Apr 7, 2026 | 60%17 items | 45.5 |
| 55 | Mar 18, 2026 | 60%15 items | 42.5 | |
| 56 | Jul 30, 2026 | 80%21 items | 42.1 |
Not yet ranked
These models have partial scores and will receive a rank when evidence is complete.
| 67.5 | Fewer than 3 coding evaluation types |