# DeepSeek LLM 67B vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-minimax-m2-7
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and MiniMax-M2.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.7 to 7.0.

## Snapshot

| | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 24.9 | 37.7 |
| Rank | 347 | 196 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- MiniMax-M2.7: 41.8 (#120)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1096 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- MiniMax-M2.7: 25.1 (#111)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- MiniMax-M2.7: 19.7 (#253)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1422 |
| Epoch Capabilities Index | 110.5 | 145.85 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 39.3% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- MiniMax-M2.7: 25.9 (#263)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1108 | 1420 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| ProofBench | — | 3% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- MiniMax-M2.7: 37.7 (#152)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 12.9% |
| LMArena Expert | — | 1444 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- MiniMax-M2.7: 50.3 (#123)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1073 | 1382 |
| LMArena Chinese | 1132 | 1441 |
| LMArena French | — | 1421 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1313 |
| LMArena Russian | — | 1383 |
| LMArena Spanish | — | 1403 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- MiniMax-M2.7: 74.1 (#103)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1405 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- MiniMax-M2.7: 43.3 (#99)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1092 | 1419 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- MiniMax-M2.7: 58.9 (#112)

| Benchmark | DeepSeek LLM 67B | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1105 | 1405 |
| LMArena Creative Writing | 1067 | 1354 |
| LMArena Multi-Turn | 1082 | 1412 |

## FAQ

### Is DeepSeek LLM 67B better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and MiniMax-M2.7 share?

11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and MiniMax-M2.7 has 30.