Model comparison
MiMo-V2-Flash vs Qwen3-Coder 480B-A35B Instruct
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 38.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. MiMo-V2-Flash scores higher in 7 categories and Qwen3-Coder 480B-A35B Instruct in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Flash leads 59.7 to 55.3.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
Side by side
| MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 41.3 | 38.1 |
| Released | 2025-12-16 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.14 | $1.50 |
| Output $ / M tokens | $0.28 | $7.50 |
| Results tracked | 21 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
MiMo-V2-Flash: 36.1 (#211), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1330 | 1275 |
| LMArena Coding | 1443 | 1412 |
| ALE-Bench | 737.95 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| SciCode | 25.9% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
MiMo-V2-Flash: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Too close to call
MiMo-V2-Flash: 24.9 (#157), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| CritPt | 0% | — |
Math Too close to call
MiMo-V2-Flash: 38.3 (#139), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1396 | 1365 |
Knowledge MiMo-V2-Flash leads
MiMo-V2-Flash: 39.7 (#131), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1425 | 1338 |
Multilingual MiMo-V2-Flash leads
MiMo-V2-Flash: 51.0 (#113), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1392 | 1346 |
| LMArena Chinese | 1462 | 1357 |
| LMArena French | 1429 | 1398 |
| LMArena German | 1395 | 1325 |
| LMArena Japanese | 1325 | 1310 |
| LMArena Korean | 1358 | 1305 |
| LMArena Russian | 1387 | 1366 |
| LMArena Spanish | 1420 | 1360 |
Instruction Following MiMo-V2-Flash leads
MiMo-V2-Flash: 73.5 (#120), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1392 | 1355 |
Long Context MiMo-V2-Flash leads
MiMo-V2-Flash: 43.0 (#110), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1409 | 1378 |
Writing & Preference MiMo-V2-Flash leads
MiMo-V2-Flash: 59.7 (#106), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | MiMo-V2-Flash | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1411 | 1357 |
| LMArena Creative Writing | 1375 | 1333 |
| LMArena Multi-Turn | 1404 | 1365 |
Frequently asked questions
Is MiMo-V2-Flash better than Qwen3-Coder 480B-A35B Instruct?
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 38.1 on the Noometry Index.
Which is cheaper, MiMo-V2-Flash or Qwen3-Coder 480B-A35B Instruct?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is MiMo-V2-Flash or Qwen3-Coder 480B-A35B Instruct better for coding?
They score almost the same on coding (36.1 vs 35.5); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do MiMo-V2-Flash and Qwen3-Coder 480B-A35B Instruct share?
19 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.