Model comparison
MiniMax M1 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 40.3 on the Noometry Index. MiniMax M1 costs 3.1× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax M1 scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 37.5.
- MiniMax M1 is cheaper at $0.55 / $2.20 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- MiniMax M1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax M1 | Qwen3.8 Max | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 40.3 | 56.8 |
| Released | 2025-06-13 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 40K | 131K |
| Input $ / M tokens | $0.55 | $2 |
| Output $ / M tokens | $2.20 | $6 |
| Results tracked | 18 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
MiniMax M1: 39.9 (#153), Qwen3.8 Max: 53.5 (#29)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1359 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
MiniMax M1: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
MiniMax M1: 26.9 (#126), Qwen3.8 Max: 54.4 (#26)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1339 | 1496 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
MiniMax M1: 37.5 (#151), Qwen3.8 Max: 73.2 (#20)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1361 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
Knowledge Qwen3.8 Max leads
MiniMax M1: 36.4 (#170), Qwen3.8 Max: 61.7 (#27)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1317 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
Multimodal Not comparable
MiniMax M1: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
MiniMax M1: 45.8 (#163), Qwen3.8 Max: 56.7 (#18)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1319 | 1472 |
| LMArena Chinese | 1360 | 1538 |
| LMArena French | 1370 | 1503 |
| LMArena German | 1350 | 1483 |
| LMArena Japanese | 1217 | 1467 |
| LMArena Korean | 1266 | 1461 |
| LMArena Russian | 1329 | 1481 |
| LMArena Spanish | 1353 | 1492 |
Instruction Following Qwen3.8 Max leads
MiniMax M1: 69.3 (#174), Qwen3.8 Max: 77.6 (#17)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1312 | 1479 |
Long Context Qwen3.8 Max leads
MiniMax M1: 41.4 (#141), Qwen3.8 Max: 45.6 (#31)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1326 | 1489 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference Qwen3.8 Max leads
MiniMax M1: 53.1 (#161), Qwen3.8 Max: 67.1 (#30)
| Benchmark | MiniMax M1 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1343 | 1483 |
| LMArena Creative Writing | 1298 | 1479 |
| LMArena Multi-Turn | 1335 | 1489 |
Frequently asked questions
Is MiniMax M1 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 40.3 on the Noometry Index. MiniMax M1 costs 3.1× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, MiniMax M1 or Qwen3.8 Max?
MiniMax M1 is cheaper. It lists at $0.55 per million input tokens and $2.20 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is MiniMax M1 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do MiniMax M1 and Qwen3.8 Max share?
17 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and Qwen3.8 Max has 39.