# Codellama 70b Instruct vs MiniMax-M2.1

> MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-minimax-m2-1
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and MiniMax-M2.1 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where MiniMax-M2.1 leads 50.0 to 24.8.

## Snapshot

| | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 33.7 | 38.9 |
| Rank | 237 | 178 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- MiniMax-M2.1: 40.4 (#143)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | — | 1384 |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1421 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 623.83 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- MiniMax-M2.1: 27.9 (#98)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- MiniMax-M2.1: 16.6 (#302)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1411 |
| NYT Connections (extended) | — | 11.2% |

## Math

- Codellama 70b Instruct: —
- MiniMax-M2.1: 38.3 (#138)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | — | 1397 |

## Knowledge

- Codellama 70b Instruct: —
- MiniMax-M2.1: 38.3 (#147)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 11.8% |
| LMArena Expert | — | 1431 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- MiniMax-M2.1: 50.0 (#128)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 992 | 1378 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1404 |
| LMArena German | — | 1381 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1387 |
| LMArena Spanish | — | 1397 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- MiniMax-M2.1: 73.8 (#112)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1400 |

## Long Context

- Codellama 70b Instruct: —
- MiniMax-M2.1: 43.2 (#101)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | — | 1416 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- MiniMax-M2.1: 58.3 (#120)

| Benchmark | Codellama 70b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1057 | 1392 |
| LMArena Creative Writing | — | 1361 |
| LMArena Multi-Turn | — | 1396 |

## FAQ

### Is Codellama 70b Instruct better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and MiniMax-M2.1 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and MiniMax-M2.1 has 22.