Model comparison
Llama-3.3-70B-Instruct vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 3.4× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Meta
MiniMaxSummary
- They share 26 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 1 category and MiniMax-M3 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 30.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.1% for Llama-3.3-70B-Instruct and 71.1% for MiniMax-M3.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 128K.
Side by side
| Llama-3.3-70B-Instruct | MiniMax-M3 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 30.6 | 43.8 |
| Released | 2024-12-06 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 128K | 1M |
| Max output | 4K | 512K |
| Input $ / M tokens | $0.10 | $0.30 |
| Output $ / M tokens | $0.32 | $1.20 |
| Results tracked | 43 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Llama-3.3-70B-Instruct: 31.0 (#290), MiniMax-M3: 41.8 (#118)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| SciCode | 26% | 47.1% |
| LMArena Coding | 1268 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 25.8 (#105), MiniMax-M3: 22.6 (#130)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| Berkeley Function Calling Leaderboard | 31.9% | — |
| OSWorld 2.0 | — | 4.6% |
| BALROG | 23% | — |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Llama-3.3-70B-Instruct: 14.1 (#327), MiniMax-M3: 30.1 (#87)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| SimpleBench | 19.9% | 45.8% |
| CritPt | 0% | 3.7% |
| LMArena Hard Prompts | 1257 | 1447 |
| DTBench | 59.5% | 78.9% |
| LMCA | 17.5% | 33.7% |
| Epoch Capabilities Index | 127.33 | 146.95 |
| ForecastBench | 58.6 | 61.4 |
| NYT Connections (extended) | — | 65.1% |
| Chess Puzzles | — | 14% |
| LiveBench Reasoning | 50.8% | — |
| Mystery Game Puzzles | — | 8% |
| LiveBench Data Analysis | 49.5% | — |
| Surface Evolver Bench | — | 55% |
| LiveBench | 50.2% | — |
Math MiniMax-M3 leads
Llama-3.3-70B-Instruct: 15.3 (#298), MiniMax-M3: 40.0 (#95)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.1% | 71.1% |
| LMArena Math | 1267 | 1429 |
| ProofBench | — | 18% |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge MiniMax-M3 leads
Llama-3.3-70B-Instruct: 30.6 (#226), MiniMax-M3: 58.4 (#35)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 47.4% | 90.9% |
| LMArena Expert | 1225 | 1461 |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| MMLU | 86.3% | — |
Multimodal Not comparable
Llama-3.3-70B-Instruct: —, MiniMax-M3: 40.2 (#51)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Llama-3.3-70B-Instruct: 39.9 (#220), MiniMax-M3: 53.0 (#75)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1236 | 1420 |
| LMArena Chinese | 1217 | 1463 |
| LMArena French | 1281 | 1447 |
| LMArena German | 1251 | 1426 |
| LMArena Japanese | 1150 | 1381 |
| LMArena Korean | 1143 | 1372 |
| LMArena Russian | 1252 | 1428 |
| LMArena Spanish | 1270 | 1432 |
Instruction Following MiniMax-M3 leads
Llama-3.3-70B-Instruct: 71.1 (#157), MiniMax-M3: 75.5 (#62)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1242 | 1433 |
| LiveBench Instruction Following | 82.7% | — |
Long Context MiniMax-M3 leads
Llama-3.3-70B-Instruct: 26.4 (#295), MiniMax-M3: 44.2 (#72)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1256 | 1445 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference MiniMax-M3 leads
Llama-3.3-70B-Instruct: 47.6 (#207), MiniMax-M3: 62.1 (#83)
| Benchmark | Llama-3.3-70B-Instruct | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1274 | 1433 |
| LMArena Creative Writing | 1250 | 1404 |
| LMArena Multi-Turn | 1280 | 1442 |
| EQ-Bench 4 | — | 1150 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 3.4× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, Llama-3.3-70B-Instruct or MiniMax-M3?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is Llama-3.3-70B-Instruct or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 31.0 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 128K.
How many benchmarks do Llama-3.3-70B-Instruct and MiniMax-M3 share?
26 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and MiniMax-M3 has 41.