Model comparison
Llama 13b vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Meta
MiniMaxSummary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and MiniMax-M2 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2 leads 53.0 to 13.8.
Side by side
| Llama 13b | MiniMax-M2 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 24.4 | 37.4 |
| Released | 2023-02-24 | 2025-10-27 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 21 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Llama 13b: 21.4 (#337), MiniMax-M2: 39.3 (#159)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 683 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
Agentic & Tool Use Not comparable
Llama 13b: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
Llama 13b: 14.0 (#329), MiniMax-M2: 19.4 (#258)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 728 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math MiniMax-M2 leads
Llama 13b: 26.7 (#256), MiniMax-M2: 37.3 (#160)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Math | 838 | 1352 |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, MiniMax-M2: 37.0 (#163)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Expert | — | 1337 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, MiniMax-M2: —
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual MiniMax-M2 leads
Llama 13b: 16.6 (#297), MiniMax-M2: 45.3 (#171)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 819 | 1313 |
| LMArena Chinese | — | 1366 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1326 |
Instruction Following MiniMax-M2 leads
Llama 13b: 36.7 (#305), MiniMax-M2: 70.2 (#166)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 781 | 1328 |
Long Context Not comparable
Llama 13b: —, MiniMax-M2: 40.5 (#153)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1331 |
Writing & Preference MiniMax-M2 leads
Llama 13b: 13.8 (#312), MiniMax-M2: 53.0 (#162)
| Benchmark | Llama 13b | MiniMax-M2 |
|---|---|---|
| LMArena Text | 834 | 1340 |
| LMArena Creative Writing | 794 | 1286 |
| LMArena Multi-Turn | 753 | 1361 |
Frequently asked questions
Is Llama 13b better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 24.4 on the Noometry Index.
Is Llama 13b or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and MiniMax-M2 share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and MiniMax-M2 has 21.