Model comparison
Llama-3.3-70B-Instruct vs MiniMax M1
MiniMax M1 is the stronger model overall, scoring 39.7 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 5.5× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Meta
MiniMaxSummary
- They share 18 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 1 category and MiniMax M1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax M1 leads 34.8 to 14.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 33.3% for Llama-3.3-70B-Instruct and 69.4% for MiniMax M1.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.40 / $2.20 for MiniMax M1.
- MiniMax M1 accepts more context: 1M tokens versus 128K.
Side by side
| Llama-3.3-70B-Instruct | MiniMax M1 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 30.3 | 39.7 |
| Released | 2024-12-06 | 2025-06-13 |
| Weights | Open | Open |
| Context window | 128K | 1M |
| Max output | 4K | 40K |
| Input $ / M tokens | $0.10 | $0.40 |
| Output $ / M tokens | $0.32 | $2.20 |
| Results tracked | 43 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
Llama-3.3-70B-Instruct: 30.6 (#284), MiniMax M1: 39.2 (#149)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1268 | 1359 |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.6 (#100), MiniMax M1: —
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning MiniMax M1 leads
Llama-3.3-70B-Instruct: 13.7 (#325), MiniMax M1: 25.8 (#125)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1340 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.32 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math MiniMax M1 leads
Llama-3.3-70B-Instruct: 14.3 (#292), MiniMax M1: 34.8 (#152)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| LMArena Math | 1268 | 1360 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge MiniMax M1 leads
Llama-3.3-70B-Instruct: 30.5 (#220), MiniMax M1: 35.7 (#168)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1225 | 1316 |
| GPQA Diamond | 47.4% | — |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| MMLU | 86.3% | — |
Multilingual MiniMax M1 leads
Llama-3.3-70B-Instruct: 40.1 (#215), MiniMax M1: 46.0 (#157)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1236 | 1320 |
| LMArena Chinese | 1217 | 1361 |
| LMArena French | 1280 | 1369 |
| LMArena German | 1251 | 1350 |
| LMArena Japanese | 1149 | 1220 |
| LMArena Korean | 1142 | 1263 |
| LMArena Russian | 1252 | 1330 |
| LMArena Spanish | 1269 | 1354 |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.3 (#152), MiniMax M1: 69.5 (#169)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1242 | 1312 |
| LiveBench Instruction Following | 82.7% | — |
Long Context MiniMax M1 leads
Llama-3.3-70B-Instruct: 26.4 (#290), MiniMax M1: 41.4 (#136)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| Fiction.LiveBench | 33.3% | 69.4% |
| LMArena Longer Query | 1256 | 1326 |
Writing & Preference MiniMax M1 leads
Llama-3.3-70B-Instruct: 47.8 (#203), MiniMax M1: 53.3 (#155)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax M1 |
|---|---|---|
| LMArena Text | 1274 | 1343 |
| LMArena Creative Writing | 1250 | 1298 |
| LMArena Multi-Turn | 1279 | 1335 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than MiniMax M1?
MiniMax M1 is the stronger model overall, scoring 39.7 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 5.5× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Which is cheaper, Llama-3.3-70B-Instruct or MiniMax M1?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; MiniMax M1 lists at $0.40 and $2.20.
Is Llama-3.3-70B-Instruct or MiniMax M1 better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.2 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
MiniMax M1 does, with 1M tokens against 128K.
How many benchmarks do Llama-3.3-70B-Instruct and MiniMax M1 share?
18 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and MiniMax M1 has 18.