Model comparison
Llama 2-70B vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 24.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
MiniMaxSummary
- They share 15 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and MiniMax-M2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2 leads 37.0 to 7.4.
Side by side
| Llama 2-70B | MiniMax-M2 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 24.4 | 37.4 |
| Released | 2023-07-18 | 2025-10-27 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Llama 2-70B: 31.4 (#286), MiniMax-M2: 39.3 (#159)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1079 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
Agentic & Tool Use Not comparable
Llama 2-70B: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
Llama 2-70B: 14.4 (#325), MiniMax-M2: 19.4 (#258)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math MiniMax-M2 leads
Llama 2-70B: 8.1 (#326), MiniMax-M2: 37.3 (#160)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1091 | 1352 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge MiniMax-M2 leads
Llama 2-70B: 7.4 (#310), MiniMax-M2: 37.0 (#163)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1039 | 1337 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual MiniMax-M2 leads
Llama 2-70B: 27.7 (#274), MiniMax-M2: 45.3 (#171)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1045 | 1313 |
| LMArena Chinese | 995 | 1366 |
| LMArena French | 1090 | 1335 |
| LMArena German | 1041 | 1355 |
| LMArena Russian | 1083 | 1331 |
| LMArena Spanish | 1143 | 1326 |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
Instruction Following MiniMax-M2 leads
Llama 2-70B: 54.9 (#278), MiniMax-M2: 70.2 (#166)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1071 | 1328 |
Long Context MiniMax-M2 leads
Llama 2-70B: 32.3 (#270), MiniMax-M2: 40.5 (#153)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1062 | 1331 |
Writing & Preference MiniMax-M2 leads
Llama 2-70B: 32.3 (#279), MiniMax-M2: 53.0 (#162)
| Benchmark | Llama 2-70B | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1115 | 1340 |
| LMArena Creative Writing | 1075 | 1286 |
| LMArena Multi-Turn | 1088 | 1361 |
Frequently asked questions
Is Llama 2-70B better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 24.4 on the Noometry Index.
Is Llama 2-70B or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and MiniMax-M2 share?
15 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and MiniMax-M2 has 21.