Model comparison
Grok 4.20 Multi-Agent vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 46.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 3 categories and MiMo-V2.6-Flash in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Flash leads 51.9 to 39.4.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 1M.
- MiMo-V2.6-Flash has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 Multi-Agent | MiMo-V2.6-Flash | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 46.2 | 48.5 |
| Released | 2026-03-09 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | 1M | 1.05M |
| Max output | 30K | 131K |
| Input $ / M tokens | $1.25 | $0.14 |
| Output $ / M tokens | $2.50 | $0.28 |
| Results tracked | 20 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
Grok 4.20 Multi-Agent: 43.0 (#92), MiMo-V2.6-Flash: 53.4 (#30)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Coding | 1457 | 1504 |
| LMArena WebDev | — | 1637 |
| SciCode | — | 51.3% |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, MiMo-V2.6-Flash: —
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Search | 1204 | — |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.9 (#48), MiMo-V2.6-Flash: 36.5 (#66)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1482 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | — | 12% |
Math MiMo-V2.6-Flash leads
Grok 4.20 Multi-Agent: 39.4 (#104), MiMo-V2.6-Flash: 51.9 (#52)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Math | 1442 | 1468 |
| ProofBench | — | 63% |
Knowledge MiMo-V2.6-Flash leads
Grok 4.20 Multi-Agent: 40.4 (#119), MiMo-V2.6-Flash: 42.2 (#99)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1445 | 1501 |
Multimodal Too close to call
Grok 4.20 Multi-Agent: 40.5 (#48), MiMo-V2.6-Flash: 40.5 (#47)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | 1259 | 1259 |
Multilingual Too close to call
Grok 4.20 Multi-Agent: 54.4 (#43), MiMo-V2.6-Flash: 54.0 (#51)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1440 | 1434 |
| LMArena Chinese | 1475 | 1511 |
| LMArena French | 1466 | 1475 |
| LMArena Russian | 1457 | 1409 |
| LMArena Spanish | 1447 | 1456 |
| LMArena German | 1456 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1416 | — |
Instruction Following MiMo-V2.6-Flash leads
Grok 4.20 Multi-Agent: 74.8 (#84), MiMo-V2.6-Flash: 76.8 (#35)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1420 | 1463 |
Long Context MiMo-V2.6-Flash leads
Grok 4.20 Multi-Agent: 43.7 (#88), MiMo-V2.6-Flash: 44.8 (#57)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1431 | 1463 |
Writing & Preference Too close to call
Grok 4.20 Multi-Agent: 64.0 (#59), MiMo-V2.6-Flash: 63.1 (#67)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1450 | 1455 |
| LMArena Creative Writing | 1436 | 1400 |
| LMArena Multi-Turn | 1452 | 1451 |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than MiMo-V2.6-Flash?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 46.2 on the Noometry Index.
Which is cheaper, Grok 4.20 Multi-Agent or MiMo-V2.6-Flash?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.
Is Grok 4.20 Multi-Agent or MiMo-V2.6-Flash better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 43.0 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 1M.
How many benchmarks do Grok 4.20 Multi-Agent and MiMo-V2.6-Flash share?
15 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and MiMo-V2.6-Flash has 19.