Grok 4.3: benchmarks, price and rank
Grok 4.3 from xAI is 92nd of 123 rated AI models on Spezia's leaderboard. It costs $1.25 in, $2.50 out per million tokens.
- 92nd of 123 rated models
- Rating 862
- Rated on 7 benchmarks
- Closed
- Released Apr 17, 2026
- 1 million tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 59th of 60 on Vending-Bench 2
- 56th of 66 on FrontierMath Tier 4
- 82nd of 98 on LMArena WebDev
Price: $1.25 in, $2.50 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- Vending-Bench 2$35
The model runs a simulated vending machine business for a year on its own: finding suppliers, ordering stock, setting prices and paying the daily fees.
59th of 60. Independent result from Epoch AI.
- SimpleQA Verified33.2%
Short factual questions with one checked answer, asked without web search.
60th of 78. Independent result from Epoch AI.
- FrontierMath42.8%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
59th of 76. Independent result from Epoch AI.
- LMArena text1,397
People put a question to two anonymous models and vote for the better answer.
85th of 107. Independent result from LMArena.
- LMArena WebDev1,357
People ask two anonymous models to build the same web page or app and vote for the better one.
82nd of 98. Independent result from LMArena.
- Finance Agent v237.7%
Real financial analysis work: finding figures in company filings and documents, multi-step calculations and written analysis.
Independent result from LLM Stats.
- GPQA Diamond88.8%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
54th of 103. Independent result from Epoch AI.
- FrontierMath Tier 414.6%
Research-level problems that take professional mathematicians days.
56th of 66. Independent result from Epoch AI.
Its full profile is in Spezia.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.