Compare / head-to-head
MiniMax M2vsMiniMax M2.1
MiniMax M2.1 leads 4 of 4 shared benchmarks. Both list the same combined token price. Both offer a 205K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 4
MiniMax M2.1 leads
Cheaper per token
Tie
list price, input + output
Larger context
Tie
both 205K tokens
Providers
MiniMax
same provider
MiniMax M2
MiniMax · released 2025-10-27
text
MiniMax M2.1
MiniMax · released 2025-12-22
text
Quality
Benchmark matrix
4 shared · 13 only MiniMax M2 · 9 only MiniMax M2.1| Benchmark | MiniMax M2 | MiniMax M2.1 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| SWE-bench Verified | 69.4% ↗ | 74% ↗ | -4.6 pt | MiniMax M2.1 |
| BrowseComp | 44% ↗ | 47.4% ↗ | -3.4 pt | MiniMax M2.1 |
| SimpleBench (SimpleBench) | 25% ↗ | 34.7% ↗ | -9.7 pt | MiniMax M2.1 |
| SWE-bench Multilingual | 56.5% ↗ | 72.5% ↗ | -16 pt | MiniMax M2.1 |
| Only MiniMax M2 reports · 13 | ||||
| LMArena Elo | 1343.4 ↗ | not reported | — | — |
| AgentCompany | 36% ↗ | not reported | — | — |
| ArtifactsBench | 66.8% ↗ | not reported | — | — |
| BrowseComp-zh | 48.5% ↗ | not reported | — | — |
| FinSearchComp-global | 65.5% ↗ | not reported | — | — |
| GAIA (text only) | 75.7% ↗ | not reported | — | — |
| HLE (w/ tools) | 31.8% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1296.6 ↗ | not reported | — | — |
| Multi-SWE-Bench | 36.2% ↗ | not reported | — | — |
| Terminal-Bench | 46.3% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 160.6 ↗ | not reported | — | — |
| xbench-DeepSearch | 72% ↗ | not reported | — | — |
| τ²-Bench | 77.2% ↗ | not reported | — | — |
| Only MiniMax M2.1 reports · 9 | ||||
| BrowseComp (context management) | not reported | 62% ↗ | — | — |
| Multi-SWE-bench | not reported | 49.4% ↗ | — | — |
| OctoCodingbench | not reported | 26.1% ↗ | — | — |
| SWE-bench Verified (Droid) | not reported | 71.3% ↗ | — | — |
| SWE-bench Verified (mini-swe-agent) | not reported | 67% ↗ | — | — |
| SWT-bench | not reported | 69.3% ↗ | — | — |
| Terminal-bench 2.0 | not reported | 47.9% ↗ | — | — |
| Toolathlon | not reported | 43.5% ↗ | — | — |
| VIBE (Average) | not reported | 88.6% ↗ | — | — |
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 M2 minus MiniMax M2.1 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 M2 | MiniMax M2.1 | Edge |
|---|---|---|---|
| Context window | 205K tokens | 205K tokens | Tie |
| Max output | 128K tokens | — | — |
| Input price / 1M | $0.3 ↗ | $0.3 ↗ | Tie |
| Output price / 1M | $1.2 ↗ | $1.2 ↗ | Tie |
| Cached input / 1M | $0.03 ↗ | $0.03 ↗ | Tie |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.5 | $1.5 | Tie |
| Modalities | text | text | Tie |
| Released | 2025-10-27 | 2025-12-22 | — |
| Cited benchmark scores | 17 | 13 | — |
Reliability
MiniMax status
Live from /statusMore matchups
MiniMax M2 vs …
Models sharing the most benchmarksMore matchups
MiniMax M2.1 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run MiniMax M2 and MiniMax M2.1 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.