Compare / head-to-head
DeepSeek V3.2vs
MiniMax M1
DeepSeek V3.2 leads 5 of 5 shared benchmarks. MiniMax M1 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
5 – 0
DeepSeek V3.2 leads
Cheaper per token
—
list price, input + output
Larger context
MiniMax M1
1M tokens
Providers
2 providers
DeepSeek · MiniMax
DeepSeek V3.2
DeepSeek · released 2025-12-01
text
- Context
- 131K
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 11 · 8 core
MiniMax M1
MiniMax · released 2025-06-16
text
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 16 · 7 core
Quality
Benchmark matrix
5 shared · 4 only DeepSeek V3.2 · 11 only MiniMax M1| Benchmark | DeepSeek V3.2 | MiniMax M1 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| SWE-bench Verified | 73.1% ↗ | 56% ↗ | +17.1 pt | DeepSeek V3.2 |
| GPQA Diamond | 82.4% ↗ | 70% ↗ | +12.4 pt | DeepSeek V3.2 |
| MMLU-Pro | 85% ↗ | 81.1% ↗ | +3.9 pt | DeepSeek V3.2 |
| AIME 2025 | 93.1% ↗ | 76.9% ↗ | +16.2 pt | DeepSeek V3.2 |
| LMArena Elo | 1424.8 ↗ | 1363.9 ↗ | +60.9 | DeepSeek V3.2 |
| Only DeepSeek V3.2 reports · 4 | ||||
| AIME 2026 | 94.2% ↗matharena | not reported | — | — |
| Humanity's Last Exam (no tools) | 25.1% ↗ | not reported | — | — |
| APEX-Agents (Mercor) | 21.3% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1361.7 ↗ | not reported | — | — |
| Only MiniMax M1 reports · 11 | ||||
| AIME 2024 | not reported | 86% ↗ | — | — |
| FullStackBench | not reported | 68.3% ↗ | — | — |
| HLE (no tools) | not reported | 8.4% ↗ | — | — |
| LiveCodeBench (24/8~25/5) | not reported | 65% ↗ | — | — |
| LongBench-v2 | not reported | 61.5% ↗ | — | — |
| MATH-500 | not reported | 96.8% ↗ | — | — |
| OpenAI-MRCR (128k) | not reported | 73.4% ↗ | — | — |
| SimpleQA | not reported | 18.5% ↗ | — | — |
| TAU-bench (airline) | not reported | 62% ↗ | — | — |
| TAU-bench (retail) | not reported | 63.5% ↗ | — | — |
| ZebraLogic | not reported | 86.8% ↗ | — | — |
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 DeepSeek V3.2 minus MiniMax M1 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 | DeepSeek V3.2 | MiniMax M1 | Edge |
|---|---|---|---|
| Context window | 131K tokens | 1M tokens | MiniMax M1 |
| Max output | 66K tokens | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text | Tie |
| Released | 2025-12-01 | 2025-06-16 | — |
| Cited benchmark scores | 11 | 16 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V3.2 vs …
Models sharing the most benchmarksMore matchups
MiniMax M1 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3.2 and MiniMax M1 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.