Model comparison
MiMo-V2.5-Pro vs Qwen3-30B-A3B
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 2.5× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 8 categories and Qwen3-30B-A3B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where MiMo-V2.5-Pro leads 45.4 to 31.0.
- The biggest single-benchmark swing is SciCode: 50.2% for MiMo-V2.5-Pro and 33.3% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 41K.
Side by side
| MiMo-V2.5-Pro | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 45.2 | 38.9 |
| Released | 2026-04-22 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 1.05M | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.43 | $0.12 |
| Output $ / M tokens | $0.87 | $0.50 |
| Results tracked | 27 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 47.4 (#60), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 50.2% | 33.3% |
| LMArena Coding | 1503 | 1416 |
| LMArena WebDev | 1479 | — |
| WeirdML | — | 29.8% |
| ALE-Bench | 899.8 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5-Pro: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 26.8 (#130), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 4% | 0.3% |
| LMArena Hard Prompts | 1488 | 1398 |
| DTBench | 84.5% | 69.3% |
| LMCA | 29.5% | 22.4% |
| Kagi LLM Benchmark | — | 54.9% |
| NYT Connections (extended) | 34.4% | — |
| Chess Puzzles | — | 8% |
| Epoch Capabilities Index | — | 139.63 |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 40.0 (#96), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1481 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| ProofBench | 22% | — |
Knowledge Too close to call
MiMo-V2.5-Pro: 42.2 (#98), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1503 | 1396 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.1 (#34), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1449 | 1372 |
| LMArena Chinese | 1507 | 1433 |
| LMArena French | 1488 | 1418 |
| LMArena German | 1458 | 1380 |
| LMArena Japanese | 1412 | 1337 |
| LMArena Korean | 1437 | 1331 |
| LMArena Russian | 1450 | 1370 |
| LMArena Spanish | 1471 | 1404 |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.5 (#21), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1363 |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#37), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1483 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.3 (#49), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | MiMo-V2.5-Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1465 | 1384 |
| LMArena Creative Writing | 1440 | 1317 |
| LMArena Multi-Turn | 1477 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Qwen3-30B-A3B?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 2.5× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.5-Pro or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is MiMo-V2.5-Pro or Qwen3-30B-A3B better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 41K.
How many benchmarks do MiMo-V2.5-Pro and Qwen3-30B-A3B share?
21 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen3-30B-A3B has 32.