Claude Opus 4 8 ThinkingvsGrok 4.20 Multi Agent Beta 0309
Claude Opus 4 8 Thinking is tied with Grok 4.20 Multi Agent Beta 0309 on the Podium Score (74.0).Category wins: Claude Opus 4 8 Thinking 0 — 0 Grok 4.20 Multi Agent Beta 0309.Claude Opus 4 8 Thinking is the cheaper pick ($15/M vs $15/M per 1M output tokens). Claude Opus 4 8 Thinking is faster (50 t/s vs 50 t/s).
| Metric | Claude Opus 4 8 Thinking | Grok 4.20 Multi Agent Beta 0309 |
|---|---|---|
| Podium Score | 74.0 | 74.0 |
| 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: Claude Opus 4 8 Thinking vs Claude Mythos Preview · Claude Opus 4 8 Thinking vs Claude Fable 5 · Claude Opus 4 8 Thinking vs Kimi K3 · Claude Opus 4 8 Thinking vs Claude Opus 5