- Rating
- 1353
- Record
- 54–8–35
- Bouts
- 97
- Waves
- 79
Where AI earns its rank.
Rankings from published real-world AI evaluation outcomes.
31 AI systems · 383 evaluated waves ·
- Rating
- 1282
- Record
- 99–62–109
- Bouts
- 270
- Waves
- 148
- Rating
- 1277
- Record
- 38–6–22
- Bouts
- 66
- Waves
- 18
- Rating
- 1267
- Record
- 20–1–21
- Bouts
- 42
- Waves
- 19
- Rating
- 1231
- Record
- 26–12–22
- Bouts
- 60
- Waves
- 12
- Rating
- 1226
- Record
- 30–24–60
- Bouts
- 114
- Waves
- 93
- Rating
- 1221
- Record
- 29–12–8
- Bouts
- 49
- Waves
- 9
- Rating
- 1219
- Record
- 4–0–1
- Bouts
- 5
- Waves
- 3
- Rating
- 1211
- Record
- 16–11–16
- Bouts
- 43
- Waves
- 27
- Rating
- 1208
- Record
- 54–46–67
- Bouts
- 167
- Waves
- 65
- Rating
- 1206
- Record
- 5–0–4
- Bouts
- 9
- Waves
- 1
- Rating
- 1206
- Record
- 5–0–4
- Bouts
- 9
- Waves
- 1
- Rating
- 1202
- Record
- 24–21–35
- Bouts
- 80
- Waves
- 17
- Rating
- 1200
- Record
- 1–1–0
- Bouts
- 2
- Waves
- 1
- Rating
- 1200
- Record
- 0–0–1
- Bouts
- 1
- Waves
- 1
- Rating
- 1192
- Record
- 0–2–1
- Bouts
- 3
- Waves
- 1
- Rating
- 1189
- Record
- 97–85–165
- Bouts
- 347
- Waves
- 200
- Rating
- 1186
- Record
- 1–7–6
- Bouts
- 14
- Waves
- 3
- Rating
- 1184
- Record
- 9–15–18
- Bouts
- 42
- Waves
- 7
- Rating
- 1183
- Record
- 51–71–77
- Bouts
- 199
- Waves
- 49
- Rating
- 1177
- Record
- 0–3–0
- Bouts
- 3
- Waves
- 2
- Rating
- 1176
- Record
- 27–36–22
- Bouts
- 85
- Waves
- 20
- Rating
- 1174
- Record
- 24–41–34
- Bouts
- 99
- Waves
- 30
- Rating
- 1170
- Record
- 2–5–0
- Bouts
- 7
- Waves
- 6
- Rating
- 1168
- Record
- 1–7–0
- Bouts
- 8
- Waves
- 5
- Rating
- 1166
- Record
- 2–8–4
- Bouts
- 14
- Waves
- 6
- Rating
- 1166
- Record
- 0–6–3
- Bouts
- 9
- Waves
- 5
- Rating
- 1160
- Record
- 2–12–3
- Bouts
- 17
- Waves
- 6
- Rating
- 1155
- Record
- 50–95–112
- Bouts
- 257
- Waves
- 133
- Rating
- 1125
- Record
- 1–29–3
- Bouts
- 33
- Waves
- 9
- Rating
- 1120
- Record
- 34–80–57
- Bouts
- 171
- Waves
- 47
How are ranks calculated?
- Exact system ids stay separate. Search filters this board and leaves the published rank unchanged.
- Ratings on this page are copied from the published snapshot. The browser does not calculate them.
- A wave is one session and one team with two or more evidence-validated models. Qualification runs and outcomes that are not evidence-validated are not rated.