Model comparison
Llama 2-13B vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.5 to 29.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
MiniMaxSummary
- They share 20 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.3 to 30.0.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 78.9% for MiniMax-M3.
Side by side
| Llama 2-13B | MiniMax-M3 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 29.1 | 43.5 |
| Released | 2023-07-18 | 2026-06-01 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 512K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 32 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Llama 2-13B: 30.4 (#287), MiniMax-M3: 41.5 (#111)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1062 | 1470 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Not comparable
Llama 2-13B: —, MiniMax-M3: 22.5 (#121)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Llama 2-13B: 12.3 (#333), MiniMax-M3: 29.3 (#83)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| Chess Puzzles | 0% | 14% |
| LMArena Hard Prompts | 1051 | 1447 |
| DTBench | 42.2% | 78.9% |
| Epoch Capabilities Index | 105.8 | 147 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Mystery Game Puzzles | — | 8% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| BIG-Bench Hard | 58.2% | — |
| ForecastBench | — | 61.4 |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math MiniMax-M3 leads
Llama 2-13B: 28.7 (#226), MiniMax-M3: 39.1 (#83)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1065 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
| GSM8K | 36.9% | — |
Knowledge MiniMax-M3 leads
Llama 2-13B: 27.5 (#244), MiniMax-M3: 58.4 (#32)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1030 | 1462 |
| GPQA Diamond | — | 90.9% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, MiniMax-M3: 39.5 (#45)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1254 |
| LMArena Document | — | 1435 |
| ScienceQA | 55.8% | — |
Multilingual MiniMax-M3 leads
Llama 2-13B: 26.7 (#274), MiniMax-M3: 53.2 (#70)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1024 | 1420 |
| LMArena Chinese | 1001 | 1465 |
| LMArena French | 1043 | 1445 |
| LMArena German | 1009 | 1424 |
| LMArena Japanese | 894 | 1381 |
| LMArena Korean | 953 | 1372 |
| LMArena Russian | 1055 | 1430 |
| LMArena Spanish | 1086 | 1431 |
Instruction Following MiniMax-M3 leads
Llama 2-13B: 53.5 (#282), MiniMax-M3: 75.7 (#56)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1046 | 1433 |
Long Context MiniMax-M3 leads
Llama 2-13B: 32.3 (#264), MiniMax-M3: 44.2 (#68)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1064 | 1445 |
Writing & Preference MiniMax-M3 leads
Llama 2-13B: 30.0 (#284), MiniMax-M3: 62.3 (#79)
| Benchmark | Llama 2-13B | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1085 | 1433 |
| LMArena Creative Writing | 1047 | 1405 |
| LMArena Multi-Turn | 1050 | 1441 |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Llama 2-13B better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 29.1 on the Noometry Index.
Is Llama 2-13B or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 30.4 in the Noometry coding category.
How many benchmarks do Llama 2-13B and MiniMax-M3 share?
20 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and MiniMax-M3 has 41.