Model comparison
MiMo-V2.6-Flash vs Qwen3.5 397B-A17B
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 46.0 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. MiMo-V2.6-Flash scores higher in 7 categories and Qwen3.5 397B-A17B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Flash leads 53.4 to 42.0.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 262K.
Side by side
| MiMo-V2.6-Flash | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 48.5 | 46.0 |
| Released | 2026-09-21 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.14 | $0.60 |
| Output $ / M tokens | $0.28 | $3.60 |
| Results tracked | 19 | 36 |
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: 53.4 (#30), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1637 | 1400 |
| LMArena Coding | 1504 | 1465 |
| SciCode | 51.3% | — |
Agentic & Tool Use Not comparable
MiMo-V2.6-Flash: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 36.5 (#66), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1482 | 1448 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| CritPt | 12% | — |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |
Math MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 51.9 (#52), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1468 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | 63% | — |
Knowledge Qwen3.5 397B-A17B leads
MiMo-V2.6-Flash: 42.2 (#99), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1501 | 1462 |
| GPQA Diamond | — | 86.4% |
Multimodal Too close to call
MiMo-V2.6-Flash: 40.5 (#47), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1259 | 1263 |
Multilingual Too close to call
MiMo-V2.6-Flash: 54.0 (#51), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1434 | 1430 |
| LMArena Chinese | 1511 | 1500 |
| LMArena French | 1475 | 1461 |
| LMArena Russian | 1409 | 1429 |
| LMArena Spanish | 1456 | 1441 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
Instruction Following MiMo-V2.6-Flash leads
MiMo-V2.6-Flash: 76.8 (#35), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1463 | 1424 |
Long Context Too close to call
MiMo-V2.6-Flash: 44.8 (#57), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1463 | 1442 |
Writing & Preference Too close to call
MiMo-V2.6-Flash: 63.1 (#67), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | MiMo-V2.6-Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1455 | 1438 |
| LMArena Creative Writing | 1400 | 1401 |
| LMArena Multi-Turn | 1451 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is MiMo-V2.6-Flash better than Qwen3.5 397B-A17B?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 46.0 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Flash or Qwen3.5 397B-A17B?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is MiMo-V2.6-Flash or Qwen3.5 397B-A17B better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2.6-Flash and Qwen3.5 397B-A17B share?
16 benchmarks have published results for both models. MiMo-V2.6-Flash has 19 scored results on Noometry and Qwen3.5 397B-A17B has 36.