Model comparison
Llama 3.1-70B vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
MiniMaxSummary
- They share 15 benchmarks with published results for both. Llama 3.1-70B scores higher in 1 category and MiniMax-M2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2 leads 37.3 to 13.5.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 128K.
Side by side
| Llama 3.1-70B | MiniMax-M2 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 29.6 | 37.4 |
| Released | 2024-07-23 | 2025-10-27 |
| Weights | Open | Open |
| Context window | 128K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.40 | $0.30 |
| Output $ / M tokens | $0.40 | $1.20 |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Llama 3.1-70B: 30.3 (#296), MiniMax-M2: 39.3 (#159)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1260 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Too close to call
Llama 3.1-70B: 25.1 (#112), MiniMax-M2: 25.1 (#109)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
| Vending-Bench 2 | — | 160.6 |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), MiniMax-M2: 19.4 (#258)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math MiniMax-M2 leads
Llama 3.1-70B: 13.5 (#304), MiniMax-M2: 37.3 (#160)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1252 | 1352 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge MiniMax-M2 leads
Llama 3.1-70B: 24.2 (#269), MiniMax-M2: 37.0 (#163)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1209 | 1337 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual MiniMax-M2 leads
Llama 3.1-70B: 38.8 (#225), MiniMax-M2: 45.3 (#171)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1219 | 1313 |
| LMArena Chinese | 1215 | 1366 |
| LMArena French | 1261 | 1335 |
| LMArena German | 1222 | 1355 |
| LMArena Russian | 1234 | 1331 |
| LMArena Spanish | 1253 | 1326 |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
Instruction Following MiniMax-M2 leads
Llama 3.1-70B: 65.3 (#223), MiniMax-M2: 70.2 (#166)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1231 | 1328 |
| IFEval | 82.1% | — |
Long Context MiniMax-M2 leads
Llama 3.1-70B: 37.6 (#214), MiniMax-M2: 40.5 (#153)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1241 | 1331 |
Writing & Preference MiniMax-M2 leads
Llama 3.1-70B: 35.4 (#267), MiniMax-M2: 53.0 (#162)
| Benchmark | Llama 3.1-70B | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1261 | 1340 |
| LMArena Creative Writing | 1232 | 1286 |
| LMArena Multi-Turn | 1256 | 1361 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.6 on the Noometry Index.
Which is cheaper, Llama 3.1-70B or MiniMax-M2?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is Llama 3.1-70B or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 128K.
How many benchmarks do Llama 3.1-70B and MiniMax-M2 share?
15 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and MiniMax-M2 has 21.