Model comparison
Llama 3.1-70B vs MiniMax M1
MiniMax M1 is the stronger model overall, scoring 40.3 to 29.6 on the Noometry Index. Llama 3.1-70B costs 2.4× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Meta
MiniMaxSummary
- They share 17 benchmarks with published results for both. Llama 3.1-70B 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 13.5.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.55 / $2.20 for MiniMax M1.
- MiniMax M1 accepts more context: 1M tokens versus 128K.
Side by side
| Llama 3.1-70B | MiniMax M1 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 29.6 | 40.3 |
| Released | 2024-07-23 | 2025-06-13 |
| Weights | Open | Open |
| Context window | 128K | 1M |
| Max output | 4K | 40K |
| Input $ / M tokens | $0.40 | $0.55 |
| Output $ / M tokens | $0.40 | $2.20 |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
Llama 3.1-70B: 30.3 (#296), MiniMax M1: 39.9 (#153)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1260 | 1359 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), MiniMax M1: —
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning MiniMax M1 leads
Llama 3.1-70B: 21.6 (#220), MiniMax M1: 26.9 (#126)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1339 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math MiniMax M1 leads
Llama 3.1-70B: 13.5 (#304), MiniMax M1: 37.5 (#151)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Math | 1252 | 1361 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge MiniMax M1 leads
Llama 3.1-70B: 24.2 (#269), MiniMax M1: 36.4 (#170)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1209 | 1317 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual MiniMax M1 leads
Llama 3.1-70B: 38.8 (#225), MiniMax M1: 45.8 (#163)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1219 | 1319 |
| LMArena Chinese | 1215 | 1360 |
| LMArena French | 1261 | 1370 |
| LMArena German | 1222 | 1350 |
| LMArena Japanese | 1132 | 1217 |
| LMArena Korean | 1140 | 1266 |
| LMArena Russian | 1234 | 1329 |
| LMArena Spanish | 1253 | 1353 |
Instruction Following MiniMax M1 leads
Llama 3.1-70B: 65.3 (#223), MiniMax M1: 69.3 (#174)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1231 | 1312 |
| IFEval | 82.1% | — |
Long Context MiniMax M1 leads
Llama 3.1-70B: 37.6 (#214), MiniMax M1: 41.4 (#141)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Longer Query | 1241 | 1326 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference MiniMax M1 leads
Llama 3.1-70B: 35.4 (#267), MiniMax M1: 53.1 (#161)
| Benchmark | Llama 3.1-70B | MiniMax M1 |
|---|---|---|
| LMArena Text | 1261 | 1343 |
| LMArena Creative Writing | 1232 | 1298 |
| LMArena Multi-Turn | 1256 | 1335 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than MiniMax M1?
MiniMax M1 is the stronger model overall, scoring 40.3 to 29.6 on the Noometry Index. Llama 3.1-70B costs 2.4× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-70B or MiniMax M1?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; MiniMax M1 lists at $0.55 and $2.20.
Is Llama 3.1-70B or MiniMax M1 better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.9 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
MiniMax M1 does, with 1M tokens against 128K.
How many benchmarks do Llama 3.1-70B and MiniMax M1 share?
17 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and MiniMax M1 has 18.