# Codellama 34b Instruct vs MiniMax-M2.1

> MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-minimax-m2-1
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and MiniMax-M2.1 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.5 to 28.4.

## Snapshot

| | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 30.2 | 38.4 |
| Rank | 285 | 177 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- MiniMax-M2.1: 40.1 (#132)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1046 | 1421 |
| LMArena WebDev | — | 1384 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 623.83 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- MiniMax-M2.1: 27.7 (#91)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- MiniMax-M2.1: 15.8 (#301)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1410 |
| NYT Connections (extended) | — | 11.2% |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- MiniMax-M2.1: 35.6 (#142)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1056 | 1396 |

## Knowledge

- Codellama 34b Instruct: —
- MiniMax-M2.1: 37.7 (#143)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 11.8% |
| LMArena Expert | — | 1432 |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- MiniMax-M2.1: 50.2 (#123)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1011 | 1378 |
| LMArena Chinese | 976 | 1430 |
| LMArena French | — | 1405 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1297 |
| LMArena Russian | — | 1386 |
| LMArena Spanish | — | 1396 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- MiniMax-M2.1: 74.0 (#108)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1399 |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- MiniMax-M2.1: 43.2 (#98)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1014 | 1416 |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- MiniMax-M2.1: 58.5 (#114)

| Benchmark | Codellama 34b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1066 | 1392 |
| LMArena Creative Writing | 1032 | 1362 |
| LMArena Multi-Turn | 1015 | 1396 |

## FAQ

### Is Codellama 34b Instruct better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 30.2 on the Noometry Index.

### Is Codellama 34b Instruct or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 28.0 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and MiniMax-M2.1 share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and MiniMax-M2.1 has 22.