Model comparison
Llama 13b vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
MiniMaxSummary
- They share 9 benchmarks with published results for both. Llama 13b scores higher in 0 categories and MiniMax-M3 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.1 to 13.8.
Side by side
| Llama 13b | MiniMax-M3 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 24.4 | 43.8 |
| Released | 2023-02-24 | 2026-06-01 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 512K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 21 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Llama 13b: 21.4 (#337), MiniMax-M3: 41.8 (#118)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 683 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Not comparable
Llama 13b: —, MiniMax-M3: 22.6 (#130)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Llama 13b: 14.0 (#329), MiniMax-M3: 30.1 (#87)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Hard Prompts | 728 | 1447 |
| Epoch Capabilities Index | 100.58 | 146.95 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| BIG-Bench Hard | 37.9% | — |
| ForecastBench | — | 61.4 |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math MiniMax-M3 leads
Llama 13b: 26.7 (#256), MiniMax-M3: 40.0 (#95)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Math | 838 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, MiniMax-M3: 58.4 (#35)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | — | 90.9% |
| LMArena Expert | — | 1461 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, MiniMax-M3: 40.2 (#51)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
| ScienceQA | 43.3% | — |
Multilingual MiniMax-M3 leads
Llama 13b: 16.6 (#297), MiniMax-M3: 53.0 (#75)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 819 | 1420 |
| LMArena Chinese | — | 1463 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1432 |
Instruction Following MiniMax-M3 leads
Llama 13b: 36.7 (#305), MiniMax-M3: 75.5 (#62)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 781 | 1433 |
Long Context Not comparable
Llama 13b: —, MiniMax-M3: 44.2 (#72)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | — | 1445 |
Writing & Preference MiniMax-M3 leads
Llama 13b: 13.8 (#312), MiniMax-M3: 62.1 (#83)
| Benchmark | Llama 13b | MiniMax-M3 |
|---|---|---|
| LMArena Text | 834 | 1433 |
| LMArena Creative Writing | 794 | 1404 |
| LMArena Multi-Turn | 753 | 1442 |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Llama 13b better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 24.4 on the Noometry Index.
Is Llama 13b or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and MiniMax-M3 share?
9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and MiniMax-M3 has 41.