Model comparison
Llama 2-7B vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 29.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
MiniMaxSummary
- They share 15 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and MiniMax-M2.1 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 28.0.
Side by side
| Llama 2-7B | MiniMax-M2.1 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 29.1 | 38.9 |
| Released | 2023-07-18 | 2025-12-23 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 29 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Llama 2-7B: 29.2 (#307), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1002 | 1421 |
| LMArena WebDev | — | 1384 |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Not comparable
Llama 2-7B: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Too close to call
Llama 2-7B: 15.7 (#312), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1411 |
| NYT Connections (extended) | — | 11.2% |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 99.06 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math MiniMax-M2.1 leads
Llama 2-7B: 30.7 (#233), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1042 | 1397 |
| GSM8K | 16.7% | — |
Knowledge MiniMax-M2.1 leads
Llama 2-7B: 28.2 (#248), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1036 | 1431 |
| Vectara Hallucination Rate | — | 11.8% |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, MiniMax-M2.1: —
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual MiniMax-M2.1 leads
Llama 2-7B: 23.8 (#293), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 973 | 1378 |
| LMArena Chinese | 973 | 1430 |
| LMArena French | 970 | 1404 |
| LMArena German | 978 | 1381 |
| LMArena Russian | 995 | 1387 |
| LMArena Spanish | 1007 | 1397 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1298 |
Instruction Following MiniMax-M2.1 leads
Llama 2-7B: 50.8 (#298), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1006 | 1400 |
Long Context MiniMax-M2.1 leads
Llama 2-7B: 30.4 (#287), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 999 | 1416 |
Writing & Preference MiniMax-M2.1 leads
Llama 2-7B: 28.0 (#298), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Llama 2-7B | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1053 | 1392 |
| LMArena Creative Writing | 1033 | 1361 |
| LMArena Multi-Turn | 1029 | 1396 |
Frequently asked questions
Is Llama 2-7B better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 29.1 on the Noometry Index.
Is Llama 2-7B or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and MiniMax-M2.1 share?
15 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and MiniMax-M2.1 has 22.