Model comparison
Llama 3-70B vs MiniMax M1
MiniMax M1 is the stronger model overall, scoring 40.3 to 28.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
MiniMaxSummary
- They share 17 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and MiniMax M1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax M1 leads 37.5 to 12.8.
Side by side
| Llama 3-70B | MiniMax M1 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 28.8 | 40.3 |
| Released | 2024-04-18 | 2025-06-13 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 40K |
| Input $ / M tokens | — | $0.55 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 31 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
Llama 3-70B: 35.8 (#218), MiniMax M1: 39.9 (#153)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1206 | 1359 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), MiniMax M1: —
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| Cybench | 5% | — |
Reasoning MiniMax M1 leads
Llama 3-70B: 18.0 (#288), MiniMax M1: 26.9 (#126)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1339 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math MiniMax M1 leads
Llama 3-70B: 12.8 (#305), MiniMax M1: 37.5 (#151)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Math | 1218 | 1361 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge MiniMax M1 leads
Llama 3-70B: 20.8 (#277), MiniMax M1: 36.4 (#170)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1149 | 1317 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |
Multilingual MiniMax M1 leads
Llama 3-70B: 33.6 (#251), MiniMax M1: 45.8 (#163)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1142 | 1319 |
| LMArena Chinese | 1114 | 1360 |
| LMArena French | 1232 | 1370 |
| LMArena German | 1169 | 1350 |
| LMArena Japanese | 1017 | 1217 |
| LMArena Korean | 1017 | 1266 |
| LMArena Russian | 1159 | 1329 |
| LMArena Spanish | 1241 | 1353 |
Instruction Following MiniMax M1 leads
Llama 3-70B: 62.5 (#238), MiniMax M1: 69.3 (#174)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1194 | 1312 |
Long Context MiniMax M1 leads
Llama 3-70B: 35.6 (#240), MiniMax M1: 41.4 (#141)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Longer Query | 1174 | 1326 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference MiniMax M1 leads
Llama 3-70B: 42.8 (#231), MiniMax M1: 53.1 (#161)
| Benchmark | Llama 3-70B | MiniMax M1 |
|---|---|---|
| LMArena Text | 1221 | 1343 |
| LMArena Creative Writing | 1210 | 1298 |
| LMArena Multi-Turn | 1223 | 1335 |
Frequently asked questions
Is Llama 3-70B better than MiniMax M1?
MiniMax M1 is the stronger model overall, scoring 40.3 to 28.8 on the Noometry Index.
Is Llama 3-70B or MiniMax M1 better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.9 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and MiniMax M1 share?
17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and MiniMax M1 has 18.