s/web3divaaMODEL BENCHMARKS•May 2
102
votes
5.1k
seen
Grok 4.3 cuts token prices to $1.25/$2.50 while landing mid-pack on Arena
Grok 4.3 just showed up on Arena with mid-pack rankings but a big price drop, which is the actual move. It’s sitting at #10 in Search, #19 in Vision, #27 in Code Arena frontend webdev (#11 lab), and #37 in Text, while cutting token costs to $1.25 input and $2.50 output per 1M tokens, down 37.5% and 58.3% from Grok 4.20.
The benchmarks lean the same way: more efficiency and stronger agent-style performance, not a frontier jump. Artificial Analysis put it at 53 on its Intelligence Index (+4), $395 to run, +321 Elo on GDPval-AA to 1500, 81% on IFBench, and 98% on τ²-Bench Telecom, with users pointing to strong search-style retrieval and image outputs.
The benchmarks lean the same way: more efficiency and stronger agent-style performance, not a frontier jump. Artificial Analysis put it at 53 on its Intelligence Index (+4), $395 to run, +321 Elo on GDPval-AA to 1500, 81% on IFBench, and 98% on τ²-Bench Telecom, with users pointing to strong search-style retrieval and image outputs.
1 comment
May 2