# DeepSeek-V2.5 (Sep 2024) vs MiniMax M1

> MiniMax M1 is the stronger model overall, scoring 39.7 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-minimax-m1
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and MiniMax M1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax M1 leads 39.2 to 31.3.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 37.0 | 39.7 |
| Rank | 197 | 146 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $2.20 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- MiniMax M1: 39.2 (#149)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1310 | 1359 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- MiniMax M1: 25.8 (#125)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1340 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- MiniMax M1: 34.8 (#152)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Math | 1289 | 1360 |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- MiniMax M1: 35.7 (#168)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1266 | 1316 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- MiniMax M1: 46.0 (#157)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1273 | 1320 |
| LMArena Chinese | 1317 | 1361 |
| LMArena French | 1288 | 1369 |
| LMArena German | 1258 | 1350 |
| LMArena Japanese | 1228 | 1220 |
| LMArena Korean | 1209 | 1263 |
| LMArena Russian | 1289 | 1330 |
| LMArena Spanish | 1248 | 1354 |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- MiniMax M1: 69.5 (#169)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1312 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- MiniMax M1: 41.4 (#136)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Longer Query | 1301 | 1326 |
| Fiction.LiveBench | — | 69.4% |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- MiniMax M1: 53.3 (#155)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax M1 |
|---|---|---|
| LMArena Text | 1294 | 1343 |
| LMArena Creative Writing | 1285 | 1298 |
| LMArena Multi-Turn | 1297 | 1335 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than MiniMax M1?

MiniMax M1 is the stronger model overall, scoring 39.7 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or MiniMax M1 better for coding?

MiniMax M1 scores higher on coding benchmarks: 39.2 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiniMax M1 share?

17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiniMax M1 has 18.