Compare / head-to-head
Grok 4.20 Multi-AgentvsMiniMax M3
Grok 4.20 Multi-Agent and MiniMax M3 do not yet share a public benchmark, so quality cannot be compared apples-to-apples. MiniMax M3 is 2.5x cheaper per token. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0
no overlap yet
Cheaper per token
MiniMax M3
2.5x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
— · 100%
xAI · MiniMax
Grok 4.20 Multi-Agent
xAI · released 2026-03-09
textvision
MiniMax M3
MiniMax · released 2026-06-01
textvision
Quality
Benchmark matrix
0 shared · 0 only Grok 4.20 Multi-Agent · 3 only MiniMax M3| Benchmark | Grok 4.20 Multi-Agent | MiniMax M3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 0 | ||||
| No public benchmark is reported for both models yet. | ||||
| Only Grok 4.20 Multi-Agent reports · 0 | ||||
| Grok 4.20 Multi-Agent reports nothing MiniMax M3 does not. | ||||
| Only MiniMax M3 reports · 3 | ||||
| GPQA Diamond | not reported | 90.9% ↗epoch | — | — |
| LMArena Elo | not reported | 1433.5 ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 71.1% ↗epoch | — | — |
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 4.20 Multi-Agent minus MiniMax M3 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
Official pricing pages and model cards| Spec | Grok 4.20 Multi-Agent | MiniMax M3 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $1.25 ↗ | $0.3 ↗ | MiniMax M3 |
| Output price / 1M | $2.5 ↗ | $1.2 ↗ | MiniMax M3 |
| Cached input / 1M | $0.2 ↗ | $0.06 ↗ | MiniMax M3 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $3.75 | $1.5 | MiniMax M3 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-03-09 | 2026-06-01 | — |
| Cited benchmark scores | 0 | 3 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
MiniMax M3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Grok 4.20 Multi-Agent and MiniMax M3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.