ObviousBench

PUBLIC MODEL RELIABILITY · LAB VIEW

xAI

22 public configurations across 6 model families in the 2026-08-13 release. The global cost frontier stays available as context.

Open xAI on the cost frontier Compare the full public field

GLOBAL REFERENCE RETAINED

Where xAI sits in the complete public field

The lab is highlighted without changing the frontier calculation or zoom. This preserves the comparison frame that a provider-only chart would otherwise hide.

xAI in the global fieldAll 555 public configurations on the same global log-cost and pass3 scale as the homepage frontier. Public field xAIGlobal Pareto
xAI configurations highlighted in the global ObviousBench cost and reliability field 100% 95% 90% 80% 60% 40% 20% 10% Grok 4.1 Fast · None / disabled · 55.6% · $0.01734 Grok 4.20 · None / disabled · 56.9% · $0.02048 Grok 4.3 · None / disabled · 48.6% · $0.01591 Grok 4.1 Fast · Reasoning · 93.8% · $0.07883 Grok 4.20 · Low · 98.6% · $0.8517 Grok 4.3 · Low · 96.5% · $0.3436 Grok Build 0.1 · Low · 98.6% · $0.6452 Grok 4.20 · Medium · 98.6% · $0.8313 Grok 4.3 · Medium · 97.9% · $0.5694 Grok Build 0.1 · Medium · 99.3% · $0.6388 Grok 4.20 · High · 98.6% · $0.8269 Grok 4.3 · High · 98.6% · $0.4246 Grok Build 0.1 · High · 99.3% · $0.6161 Grok 4.20 · Extra high · 97.2% · $0.8436 Grok 4.3 · Extra high · 97.9% · $0.4158 Grok Build 0.1 · Extra high · 97.2% · $0.6303 Grok 4.5 · Low · 100% · $0.5465 Grok 4.6 · Low · 99.3% · $0.5567 Grok 4.5 · Medium · 100% · $0.6477 Grok 4.6 · Medium · 100% · $0.7495 Grok 4.5 · High · 100% · $0.6594 Grok 4.6 · High · 100% · $0.7911 More expensive Cheaper

This is a fixed global reference, not a recomputed xAI frontier. Hover a highlighted point for its observed setting, then select it to continue in the interactive cost frontier.

CURATED DETAIL

Decision pages for xAI

These highlighted cards have an indexable evidence page. The rest remain in the full explorer rather than being turned into thin pages.

Grok 4.5Best observed 100% · $0.5465 Grok 4.6Best observed 100% · $0.7495

FULL LAB VIEW

All observed xAI model families

Sorted by highest observed answer pass3, then the lowest cost at that score. Release dates are not inferred because this release data does not encode a consistent vendor release-date field.

Grok 4.5Best observed 100% · $0.5465 Grok 4.6Best observed 100% · $0.7495
Grok Build 0.1Best observed 99.3% · $0.6161
Grok 4.3Best observed 98.6% · $0.4246
Grok 4.20Best observed 98.6% · $0.8269
Grok 4.1 FastBest observed 93.8% · $0.07883