Grok 4.20 Beta1vsClaude Sonnet 4 5 20250929 Thinking 32k
Grok 4.20 Beta1 leads the overall Podium Score by 1.0 points (74.0 vs 73.0).Category wins: Grok 4.20 Beta1 0 — 0 Claude Sonnet 4 5 20250929 Thinking 32k.Grok 4.20 Beta1 is the cheaper pick ($15/M vs $15/M per 1M output tokens). Grok 4.20 Beta1 is faster (50 t/s vs 50 t/s).
| Metric | Grok 4.20 Beta1 | Claude Sonnet 4 5 20250929 Thinking 32k |
|---|---|---|
| Podium Score | 74.0 ▲ | 73.0 |
| Arena Elo | — | — |
| Intelligence Index | — | — |
| Coding | — | — |
| Math | — | — |
| Reasoning | — | — |
| Agentic | — | — |
| Knowledge | — | — |
| Multimodal | — | — |
| Long-context | — | — |
| Output speed | 50 t/s | 50 t/s |
| Output price | $15/M | $15/M |
| Context window | 128K | 128K |
Scores aggregated from five leaderboards on 2026-08-05. See Methodology. More head-to-heads: Grok 4.20 Beta1 vs Claude Mythos Preview · Grok 4.20 Beta1 vs Claude Fable 5 · Grok 4.20 Beta1 vs Kimi K3 · Grok 4.20 Beta1 vs Claude Opus 5