Compare / head-to-head
MiniMax M3vso3
MiniMax M3 and o3 split their 2 shared benchmarks evenly. MiniMax M3 is 6.7x cheaper per token. MiniMax M3 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 1
even split
Cheaper per token
MiniMax M3
6.7x cheaper, input + output
Larger context
MiniMax M3
1M tokens
Provider uptime (30d)
100% · 94.2446%
MiniMax · OpenAI
MiniMax M3
MiniMax · released 2026-06-01
textvision
Quality
Benchmark matrix
2 shared · 1 only MiniMax M3 · 5 only o3| Benchmark | MiniMax M3 | o3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 90.9% ↗epoch | 81.8% ↗epoch | +9.1 pt | MiniMax M3 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 71.1% ↗epoch | 84.4% ↗epoch | -13.3 pt | o3 |
| Only MiniMax M3 reports · 1 | ||||
| LMArena Elo | 1433.5 ↗ | not reported | — | — |
| Only o3 reports · 5 | ||||
| SWE-bench Verified | not reported | 69.1% ↗ | — | — |
| AIME 2025 | not reported | 89.2% ↗matharena ⚠ | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 33.3% ↗epoch | — | — |
| SimpleQA Verified | not reported | 49.4% ↗epoch | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 62.3% ↗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 MiniMax M3 minus o3 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 | MiniMax M3 | o3 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 200K tokens | MiniMax M3 |
| Max output | — | 100K tokens | — |
| Input price / 1M | $0.3 ↗ | $2 ↗ | MiniMax M3 |
| Output price / 1M | $1.2 ↗ | $8 ↗ | MiniMax M3 |
| Cached input / 1M | $0.06 ↗ | $0.5 ↗ | MiniMax M3 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.5 | $10 | MiniMax M3 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-06-01 | 2025-04-16 | — |
| Cited benchmark scores | 3 | 7 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
MiniMax M3 vs …
Models sharing the most benchmarksMore matchups
o3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run MiniMax M3 and o3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.