Grok 4.6 vs Gemini 3.1 Ultra

Head-to-head technical comparison of intelligence, capabilities, and API pricing.

Grok 4.6
xAI
AI Mastery Index93.8
LMSYS Arena1470
Technical (MMLU-Pro)93.1%
Cost per 1M Tokens$2
Gemini 3.1 Ultra
Google
AI Mastery Index92.5
LMSYS Arena1480
Technical (MMLU-Pro)92.5%
Cost per 1M Tokens$20

Which should you use?

Grok 4.6 leads on the composite index by 1.3 points (93.8 vs 92.5).

Their Arena Elo differs by only 10 points, inside the confidence intervals the public board reports, so human preference does not separate them.

Cost is the sharper difference: Gemini 3.1 Ultra is 10x the input price of Grok 4.6 ($20 against $2 per 1M), so at volume the choice is usually decided by budget rather than benchmarks.

Pick Grok 4.6 when

  • Higher composite index — 93.8 against 92.5, a gap of 1.3 points.
  • Stronger on MMLU-Pro: 93.1% against 92.5%.
  • Cheaper input tokens — $2 against $20 per 1M, so Gemini 3.1 Ultra costs 10x as much to feed.
  • Better value per point of measured capability: $0.021 per index point against $0.216.

Pick Gemini 3.1 Ultra when

On these measures Gemini 3.1 Ultra does not lead Grok 4.6 anywhere, so pick it only for reasons outside this table — an existing integration, a region, or a contract.

Value per point of measured capability, at list input pricing: Grok 4.6 $0.021 · Gemini 3.1 Ultra $0.216 per index point. Run your own token mix through the token cost calculator — a comparison at list price ignores caching and batch discounts, which move real bills more than this gap does.

Our reporting on xAI and Google