Model comparison
MiniMax-M3 vs Qwen3-Next 80B-A3B Instruct
MiniMax-M3 and Qwen3-Next 80B-A3B Instruct score almost the same on the Noometry Index (43.8 vs 43.0), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M3 scores higher in 6 categories and Qwen3-Next 80B-A3B Instruct in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 41.8.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
- MiniMax-M3 accepts more context: 1M tokens versus 131K.
Side by side
| MiniMax-M3 | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.8 | 43.0 |
| Released | 2026-06-01 | 2025-09 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 512K | 33K |
| Input $ / M tokens | $0.30 | $0.50 |
| Output $ / M tokens | $1.20 | $2 |
| Results tracked | 41 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
MiniMax-M3: 41.8 (#118), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1469 | 1440 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
MiniMax-M3: 30.1 (#87), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1428 |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | — | 66.7% |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1429 | 1440 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| Omni-MATH | — | 46.7% |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1461 | 1417 |
| GPQA Diamond | 90.9% | — |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual Too close to call
MiniMax-M3: 53.0 (#75), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1420 | 1407 |
| LMArena Chinese | 1463 | 1460 |
| LMArena French | 1447 | 1413 |
| LMArena German | 1426 | 1417 |
| LMArena Japanese | 1381 | 1395 |
| LMArena Korean | 1372 | 1364 |
| LMArena Russian | 1428 | 1404 |
| LMArena Spanish | 1432 | 1435 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | 1389 |
| IFEval | — | 81% |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1445 | 1403 |
| Fiction.LiveBench | — | 55.6% |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | MiniMax-M3 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1433 | 1417 |
| LMArena Creative Writing | 1404 | 1334 |
| LMArena Multi-Turn | 1442 | 1416 |
| WildBench | — | 80.7% |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Qwen3-Next 80B-A3B Instruct?
MiniMax-M3 and Qwen3-Next 80B-A3B Instruct score almost the same on the Noometry Index (43.8 vs 43.0), so choose on price, context window or the category you care about most.
Which is cheaper, MiniMax-M3 or Qwen3-Next 80B-A3B Instruct?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.
Is MiniMax-M3 or Qwen3-Next 80B-A3B Instruct better for coding?
They score almost the same on coding (41.8 vs 42.5); test both on your own repository before choosing.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 131K.
How many benchmarks do MiniMax-M3 and Qwen3-Next 80B-A3B Instruct share?
17 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.