# DeepSeek V4 Pro vs MiniMax M1

> DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 40.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-pro-vs-minimax-m1
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and MiniMax M1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 26.9.
- Both cost about the same: $0.66 input and $1.98 output per million tokens.

## Snapshot

| | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 54.3 | 40.3 |
| Rank | 31 | 150 |
| Context | 1M | 1M |
| Input $/M | $0.66 | $0.55 |
| Output $/M | $1.98 | $2.20 |
| Weights | Open | Open |

## Coding

- DeepSeek V4 Pro: 52.4 (#34)
- MiniMax M1: 39.9 (#153)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1470 | 1359 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |

## Agentic & Tool Use

- DeepSeek V4 Pro: 32.8 (#58)
- MiniMax M1: —

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |

## Reasoning

- DeepSeek V4 Pro: 56.5 (#24)
- MiniMax M1: 26.9 (#126)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1339 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |

## Math

- DeepSeek V4 Pro: 64.8 (#30)
- MiniMax M1: 37.5 (#151)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Math | 1455 | 1361 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |

## Knowledge

- DeepSeek V4 Pro: 59.5 (#31)
- MiniMax M1: 36.4 (#170)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1464 | 1317 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |

## Multilingual

- DeepSeek V4 Pro: 54.4 (#45)
- MiniMax M1: 45.8 (#163)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1439 | 1319 |
| LMArena Chinese | 1486 | 1360 |
| LMArena French | 1472 | 1370 |
| LMArena German | 1458 | 1350 |
| LMArena Japanese | 1445 | 1217 |
| LMArena Korean | 1447 | 1266 |
| LMArena Russian | 1453 | 1329 |
| LMArena Spanish | 1458 | 1353 |

## Instruction Following

- DeepSeek V4 Pro: 76.1 (#47)
- MiniMax M1: 69.3 (#174)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1448 | 1312 |

## Long Context

- DeepSeek V4 Pro: 45.0 (#51)
- MiniMax M1: 41.4 (#141)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Longer Query | 1458 | 1326 |
| Fiction.LiveBench | — | 69.4% |
| CL-bench Life | 13.5% | — |

## Writing & Preference

- DeepSeek V4 Pro: 65.5 (#46)
- MiniMax M1: 53.1 (#161)

| Benchmark | DeepSeek V4 Pro | MiniMax M1 |
|---|---|---|
| LMArena Text | 1451 | 1343 |
| LMArena Creative Writing | 1446 | 1298 |
| LMArena Multi-Turn | 1467 | 1335 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |

## FAQ

### Is DeepSeek V4 Pro better than MiniMax M1?

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 40.3 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Pro or MiniMax M1?

MiniMax M1 is cheaper. It lists at $0.55 per million input tokens and $2.20 per million output tokens; DeepSeek V4 Pro lists at $0.66 and $1.98.

### Is DeepSeek V4 Pro or MiniMax M1 better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 39.9 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do DeepSeek V4 Pro and MiniMax M1 share?

17 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and MiniMax M1 has 18.