Model comparison
MiMo-V2.5-Pro vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 5.5× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 0 categories and Qwen3.8 Max in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 40.0.
- The biggest single-benchmark swing is NYT Connections (extended): 34.4% for MiMo-V2.5-Pro and 88.3% for Qwen3.8 Max.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 1M.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5-Pro | Qwen3.8 Max | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 45.2 | 56.8 |
| Released | 2026-04-22 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.43 | $2 |
| Output $ / M tokens | $0.87 | $6 |
| Results tracked | 27 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
MiMo-V2.5-Pro: 47.4 (#60), Qwen3.8 Max: 53.5 (#29)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1479 | 1674 |
| SciCode | 50.2% | 53.2% |
| LMArena Coding | 1503 | 1502 |
| DeepSWE | — | 57.5% |
| FrontierSWE | — | 17.8% |
| ALE-Bench | 899.8 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5-Pro: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
MiMo-V2.5-Pro: 26.8 (#130), Qwen3.8 Max: 54.4 (#26)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 34.4% | 88.3% |
| CritPt | 4% | 20% |
| LMArena Hard Prompts | 1488 | 1496 |
| DTBench | 84.5% | 92% |
| LMCA | 29.5% | 46.2% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
MiMo-V2.5-Pro: 40.0 (#96), Qwen3.8 Max: 73.2 (#20)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| ProofBench | 22% | 58% |
| LMArena Math | 1481 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
Knowledge Qwen3.8 Max leads
MiMo-V2.5-Pro: 42.2 (#98), Qwen3.8 Max: 61.7 (#27)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1503 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
Multimodal Not comparable
MiMo-V2.5-Pro: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
MiMo-V2.5-Pro: 55.1 (#34), Qwen3.8 Max: 56.7 (#18)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1449 | 1472 |
| LMArena Chinese | 1507 | 1538 |
| LMArena French | 1488 | 1503 |
| LMArena German | 1458 | 1483 |
| LMArena Japanese | 1412 | 1467 |
| LMArena Korean | 1437 | 1461 |
| LMArena Russian | 1450 | 1481 |
| LMArena Spanish | 1471 | 1492 |
Instruction Following Too close to call
MiMo-V2.5-Pro: 77.5 (#21), Qwen3.8 Max: 77.6 (#17)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1477 | 1479 |
Long Context Too close to call
MiMo-V2.5-Pro: 45.4 (#37), Qwen3.8 Max: 45.6 (#31)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1483 | 1489 |
Writing & Preference Qwen3.8 Max leads
MiMo-V2.5-Pro: 65.3 (#49), Qwen3.8 Max: 67.1 (#30)
| Benchmark | MiMo-V2.5-Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1465 | 1483 |
| LMArena Creative Writing | 1440 | 1479 |
| LMArena Multi-Turn | 1477 | 1489 |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 5.5× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.5-Pro or Qwen3.8 Max?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is MiMo-V2.5-Pro or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 47.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 1M.
How many benchmarks do MiMo-V2.5-Pro and Qwen3.8 Max share?
24 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen3.8 Max has 39.