ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Grok 4.3vsGrok 4.6

Grok 4.6 leads 5 of 5 shared benchmarks. Grok 4.3 is 2.1x cheaper per token. Grok 4.3 has the larger context window (1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 5
Grok 4.6 leads
Cheaper per token
Grok 4.3
2.1x cheaper, input + output
Larger context
Grok 4.3
1M tokens
Provider uptime (30d)
xAI
textvision
Context
1M
Max out
Input /1M
$1.25
Output /1M
$2.5
Cached /1M
$0.2
Scores
6 · 6 core
Grok 4.6
xAI · released 2026-08-12
textvision
Context
500K
Max out
Input /1M
$2
Output /1M
$6
Cached /1M
$0.5
Scores
15 · 5 core
Quality

Benchmark matrix

BenchmarkGrok 4.3Grok 4.6ΔEdge
Reported by both · 5
GPQA Diamond88.8% epoch94% epoch-5.2 ptGrok 4.6
FrontierMath Tier 4 v2 (Epoch AI run)14.6% epoch31.7% epoch-17.1 ptGrok 4.6
FrontierMath Tiers 1-3 v2 (Epoch AI run)42.8% epoch66% epoch-23.2 ptGrok 4.6
OTIS Mock AIME 2024-2025 (Epoch AI run)93.3% epoch99.2% epoch-5.9 ptGrok 4.6
SimpleQA Verified33.2% epoch49.3% epoch-16.1 ptGrok 4.6
Only Grok 4.3 reports · 1
LMArena Elo1397.7 not reported
Only Grok 4.6 reports · 10
AA-Briefcasenot reported1577
APEX-Agentsnot reported57.5%
APEX-SWEnot reported56.4%
Artificial Analysis Intelligence Indexnot reported61
CursorBench 3.2not reported69.9%
DeepSWE v1.1not reported65.9%
FrontierCode v1.1 (Extended)not reported61.3%
GDPVal-AA v2not reported1753
Harvey LAB (Vals)not reported15.8%
Terminal-Bench 3.0not reported26%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Grok 4.3 minus Grok 4.6 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGrok 4.3Grok 4.6Edge
Context window1M tokens500K tokensGrok 4.3
Max output
Input price / 1M$1.25 $2 Grok 4.3
Output price / 1M$2.5 $6 Grok 4.3
Cached input / 1M$0.2 $0.5 Grok 4.3
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$3.75$8Grok 4.3
Modalitiestext · visiontext · visionTie
Released2026-08-12
Cited benchmark scores615
Reliability

xAI status

All providers
More matchups

Grok 4.3 vs …

More matchups

Grok 4.6 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Grok 4.3 and Grok 4.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.