# Deepseek Coder v2 vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 35.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 2 categories and MiniMax-M2.7 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 59.1 to 38.4.

## Snapshot

| | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 35.3 | 37.4 |
| Rank | 217 | 188 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1251 | 1454 |
| LMArena WebDev | — | 1397 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 599.25 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1422 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.84 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1241 | 1420 |
| ProofBench | — | 3% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1181 | 1443 |
| Vectara Hallucination Rate | — | 12.9% |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1182 | 1382 |
| LMArena Chinese | 1201 | 1439 |
| LMArena French | 1184 | 1422 |
| LMArena German | 1164 | 1398 |
| LMArena Japanese | 1126 | 1261 |
| LMArena Korean | 1104 | 1313 |
| LMArena Russian | 1188 | 1383 |
| LMArena Spanish | 1153 | 1403 |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1404 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1219 | 1419 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Deepseek Coder v2 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1191 | 1404 |
| LMArena Creative Writing | 1120 | 1354 |
| LMArena Multi-Turn | 1176 | 1413 |

## FAQ

### Is Deepseek Coder v2 better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 35.3 on the Noometry Index.

### Is Deepseek Coder v2 or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 37.5 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and MiniMax-M2.7 share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and MiniMax-M2.7 has 30.