Model comparison
MiMo-V2.6-Flash vs Qwen3-30B-A3B
MiMo-V2.6-Flash is the stronger model overall, scoring 44.4 to 38.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. MiMo-V2.6-Flash 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-V2.6-Flash leads 44.8 to 31.0.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 41K.
Side by side
| MiMo-V2.6-Flash | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 44.4 | 38.5 |
| Released | 2026-09-22 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 1.05M | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.14 | $0.12 |
| Output $ / M tokens | $0.28 | $0.50 |
| Results tracked | 13 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 44.3 (#68), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1516 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
Agentic & Tool Use Not comparable
MiMo-V2.6-Flash: —, Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 29.6 (#82), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
Math MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 37.4 (#97), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1477 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
Knowledge Too close to call
MiMo-V2.6-Flash: 42.0 (#91), Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1516 | 1395 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
Multimodal Not comparable
MiMo-V2.6-Flash: 40.2 (#39), Qwen3-30B-A3B: —
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1266 | — |
Multilingual MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 54.6 (#41), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1439 | 1372 |
| LMArena Chinese | 1501 | 1434 |
| LMArena Russian | 1424 | 1369 |
| LMArena French | — | 1419 |
| LMArena German | — | 1379 |
| LMArena Japanese | — | 1338 |
| LMArena Korean | — | 1333 |
| LMArena Spanish | — | 1403 |
Instruction Following MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 77.0 (#33), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1463 | 1364 |
Long Context MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 44.8 (#52), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1465 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 63.9 (#61), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | MiMo-V2.6-Flash | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1459 | 1384 |
| LMArena Creative Writing | 1408 | 1318 |
| LMArena Multi-Turn | 1460 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is MiMo-V2.6-Flash better than Qwen3-30B-A3B?
MiMo-V2.6-Flash is the stronger model overall, scoring 44.4 to 38.5 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Flash or Qwen3-30B-A3B?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.
Is MiMo-V2.6-Flash or Qwen3-30B-A3B better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 44.3 versus 37.0 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 41K.
How many benchmarks do MiMo-V2.6-Flash and Qwen3-30B-A3B share?
12 benchmarks have published results for both models. MiMo-V2.6-Flash has 13 scored results on Noometry and Qwen3-30B-A3B has 32.