# DeepSeek V4 Flash vs MiniMax-M2

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and MiniMax-M2 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 19.4.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4 Flash and 14.8% for MiniMax-M2.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 205K.

## Snapshot

| | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 53.6 | 37.4 |
| Rank | 35 | 204 |
| Context | 1M | 205K |
| Input $/M | $0.15 | $0.30 |
| Output $/M | $0.60 | $1.20 |
| Weights | Open | Open |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- MiniMax-M2: 39.3 (#159)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1582 | 1297 |
| LMArena Coding | 1457 | 1370 |
| FrontierCode | 18.8% | — |
| SWE-bench Verified (bash only) | — | 61% |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |

## Agentic & Tool Use

- DeepSeek V4 Flash: —
- MiniMax-M2: 25.1 (#109)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- MiniMax-M2: 19.4 (#258)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 57.8% |
| NYT Connections (extended) | 89.6% | 14.8% |
| LMArena Hard Prompts | 1444 | 1357 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.49 | — |

## Math

- DeepSeek V4 Flash: 60.3 (#37)
- MiniMax-M2: 37.3 (#160)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1427 | 1352 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- MiniMax-M2: 37.0 (#163)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1441 | 1337 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- MiniMax-M2: 45.3 (#171)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1420 | 1313 |
| LMArena Chinese | 1468 | 1366 |
| LMArena French | 1439 | 1335 |
| LMArena German | 1418 | 1355 |
| LMArena Russian | 1428 | 1331 |
| LMArena Spanish | 1436 | 1326 |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- MiniMax-M2: 70.2 (#166)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1421 | 1328 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- MiniMax-M2: 40.5 (#153)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1434 | 1331 |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- MiniMax-M2: 53.0 (#162)

| Benchmark | DeepSeek V4 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1432 | 1340 |
| LMArena Creative Writing | 1403 | 1286 |
| LMArena Multi-Turn | 1449 | 1361 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is DeepSeek V4 Flash better than MiniMax-M2?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.4 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Flash or MiniMax-M2?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

### Is DeepSeek V4 Flash or MiniMax-M2 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 39.3 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4 Flash does, with 1M tokens against 205K.

### How many benchmarks do DeepSeek V4 Flash and MiniMax-M2 share?

18 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and MiniMax-M2 has 21.