# DeepSeek LLM 67B vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.5 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 71.1% for MiniMax-M3.

## Snapshot

| | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 24.8 | 43.5 |
| Rank | 341 | 81 |
| Context | — | 1M |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- MiniMax-M3: 41.5 (#111)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1096 | 1470 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- MiniMax-M3: 22.5 (#121)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- MiniMax-M3: 29.3 (#83)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| Chess Puzzles | 0% | 14% |
| LMArena Hard Prompts | 1070 | 1447 |
| Epoch Capabilities Index | 110.54 | 147 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- MiniMax-M3: 39.1 (#83)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 71.1% |
| LMArena Math | 1108 | 1432 |
| ProofBench | — | 18% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- MiniMax-M3: 58.4 (#32)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 24.6% | 90.9% |
| LMArena Expert | — | 1462 |

## Multimodal

- DeepSeek LLM 67B: —
- MiniMax-M3: 39.5 (#45)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1254 |
| LMArena Document | — | 1435 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- MiniMax-M3: 53.2 (#70)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1073 | 1420 |
| LMArena Chinese | 1132 | 1465 |
| LMArena French | — | 1445 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1430 |
| LMArena Spanish | — | 1431 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- MiniMax-M3: 75.7 (#56)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1433 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- MiniMax-M3: 44.2 (#68)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1092 | 1445 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- MiniMax-M3: 62.3 (#79)

| Benchmark | DeepSeek LLM 67B | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1105 | 1433 |
| LMArena Creative Writing | 1067 | 1405 |
| LMArena Multi-Turn | 1082 | 1441 |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is DeepSeek LLM 67B better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and MiniMax-M3 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and MiniMax-M3 has 41.