Model comparison
MiMo-V2-Flash vs Qwen3 8B
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 33.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. MiMo-V2-Flash scores higher in 5 categories and Qwen3 8B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2-Flash leads 24.9 to 16.6.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.18 / $0.70 for Qwen3 8B.
- MiMo-V2-Flash accepts more context: 262K tokens versus 131K.
Side by side
| MiMo-V2-Flash | Qwen3 8B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 41.3 | 33.7 |
| Released | 2025-12-16 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.14 | $0.18 |
| Output $ / M tokens | $0.28 | $0.70 |
| Results tracked | 21 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Flash leads
MiMo-V2-Flash: 36.1 (#211), Qwen3 8B: 34.0 (#248)
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| SciCode | 25.9% | 22.6% |
| LMArena WebDev | 1330 | — |
| LMArena Coding | 1443 | — |
| ALE-Bench | 737.95 | — |
Agentic & Tool Use Not comparable
MiMo-V2-Flash: —, Qwen3 8B: 30.2 (#78)
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning MiMo-V2-Flash leads
MiMo-V2-Flash: 24.9 (#157), Qwen3 8B: 16.6 (#303)
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| CritPt | 0% | 0% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1420 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |
Math MiMo-V2-Flash leads
MiMo-V2-Flash: 38.3 (#139), Qwen3 8B: 34.9 (#191)
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
| LMArena Math | 1396 | — |
Knowledge MiMo-V2-Flash leads
MiMo-V2-Flash: 39.7 (#131), Qwen3 8B: 36.1 (#173)
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| GPQA Diamond | — | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
| LMArena Expert | 1425 | — |
Multilingual Not comparable
MiMo-V2-Flash: 51.0 (#113), Qwen3 8B: —
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1392 | — |
| LMArena Chinese | 1462 | — |
| LMArena French | 1429 | — |
| LMArena German | 1395 | — |
| LMArena Japanese | 1325 | — |
| LMArena Korean | 1358 | — |
| LMArena Russian | 1387 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Not comparable
MiMo-V2-Flash: 73.5 (#120), Qwen3 8B: —
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1392 | — |
Long Context MiMo-V2-Flash leads
MiMo-V2-Flash: 43.0 (#110), Qwen3 8B: 37.9 (#210)
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1409 | — |
Writing & Preference Not comparable
MiMo-V2-Flash: 59.7 (#106), Qwen3 8B: —
| Benchmark | MiMo-V2-Flash | Qwen3 8B |
|---|---|---|
| LMArena Text | 1411 | — |
| LMArena Creative Writing | 1375 | — |
| LMArena Multi-Turn | 1404 | — |
Frequently asked questions
Is MiMo-V2-Flash better than Qwen3 8B?
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 33.7 on the Noometry Index.
Which is cheaper, MiMo-V2-Flash or Qwen3 8B?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.
Is MiMo-V2-Flash or Qwen3 8B better for coding?
MiMo-V2-Flash scores higher on coding benchmarks: 36.1 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Flash does, with 262K tokens against 131K.
How many benchmarks do MiMo-V2-Flash and Qwen3 8B share?
2 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Qwen3 8B has 11.