Grok 4.20 benchmark ranking on every AI leaderboard
closed weights · top 10 on 0 of 7 · released Feb 17, 2026
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 21 |  ARC-AGI-2Reasoning · as “Grok 4.20 (Reasoning)” | Reasoning | 65.1% | 78 | |
| 33 |  Text ArenaChat · as “grok-4.20-beta-0309-reasoning” | Chat | 1,471 | 100 | |
| 33 | Document ArenaVision · as “grok-4.20-beta-0309-reasoning” | Vision | 1,416 | 38 | |
| 35 | Vision ArenaVision · as “grok-4.20-beta-0309-reasoning” | Vision | 1,256 | 100 | |
| 37 |  GPQA DiamondReasoning · as “grok-4.20-0309-reasoning” | Reasoning | 89.3% | 100 | |
| 40 | Epoch ECIReasoning · as “Grok 4.20” | Reasoning | 152.0 | 100 | |
| 73 | WebDev ArenaCoding · as “grok-4.20-beta-0309-reasoning” | Coding | 1,373 | 100 |
Category ranks and more models
Sources: each leaderboard's own published results page, captured every day at 04:30 UTC. Scores exactly as each board published them; we run no evaluations. Logos via logo.dev; trademarks belong to their owners.