Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Grok 4.20
73
Grok 4.3
79
Pick Grok 4.3 if you want the stronger benchmark profile. Grok 4.20 only becomes the better choice if coding is the priority or you need the larger 2M context window.
Coding
+13.7 difference
Multimodal
+7.3 difference
Grok 4.20
Grok 4.3
$2 / $6
$1.25 / $2.5
233 t/s
209 t/s
10.33s
12.36s
2M
1M
Pick Grok 4.3 if you want the stronger benchmark profile. Grok 4.20 only becomes the better choice if coding is the priority or you need the larger 2M context window.
Grok 4.3 is clearly ahead on the provisional aggregate, 79 to 73. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Grok 4.3's sharpest advantage is in multimodal & grounded, where it averages 78.1 against 70.8. The single biggest benchmark swing on the page is MMMU-Pro, 75.2% to 78.1%. Grok 4.20 does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Grok 4.20 is also the more expensive model on tokens at $2.00 input / $6.00 output per 1M tokens, versus $1.25 input / $2.50 output per 1M tokens for Grok 4.3. That is roughly 2.4x on output cost alone. Grok 4.20 gives you the larger context window at 2M, compared with 1M for Grok 4.3.
Grok 4.3 is ahead on BenchLM's provisional leaderboard, 79 to 73. The biggest single separator in this matchup is MMMU-Pro, where the scores are 75.2% and 78.1%.
Grok 4.20 has the edge for coding in this comparison, averaging 61 versus 47.3. Grok 4.3 stays close enough that the answer can still flip depending on your workload.
Grok 4.3 has the edge for multimodal and grounded tasks in this comparison, averaging 78.1 versus 70.8. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.