Model comparison
Grok 4.20 Multi-Agent vs MiMo-V2.5
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 43.4 on the Noometry Index. MiMo-V2.5 costs 8.9× less per token, which makes it the better buy when Grok 4.20 Multi-Agent's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 5 categories and MiMo-V2.5 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 28.6.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 1M.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 Multi-Agent | MiMo-V2.5 | |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 46.2 | 43.4 |
| Released | 2026-03-09 | 2026-04-22 |
| 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 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 4.20 Multi-Agent: 43.0 (#92), MiMo-V2.5: 43.9 (#81)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1457 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| ALE-Bench | — | 513.95 |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, MiMo-V2.5: —
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Search | 1204 | — |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.9 (#48), MiMo-V2.5: 28.6 (#101)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1450 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | — | 3.7% |
Math Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 39.4 (#104), MiMo-V2.5: 36.8 (#163)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1442 | 1436 |
| ProofBench | — | 16% |
Knowledge Too close to call
Grok 4.20 Multi-Agent: 40.4 (#119), MiMo-V2.5: 40.8 (#115)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1445 | 1460 |
Multimodal Too close to call
Grok 4.20 Multi-Agent: 40.5 (#48), MiMo-V2.5: 39.8 (#54)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1259 | 1247 |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 54.4 (#43), MiMo-V2.5: 51.9 (#99)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1440 | 1404 |
| LMArena Chinese | 1475 | 1468 |
| LMArena French | 1466 | 1447 |
| LMArena German | 1456 | 1421 |
| LMArena Japanese | 1405 | 1306 |
| LMArena Korean | 1416 | 1363 |
| LMArena Russian | 1457 | 1395 |
| LMArena Spanish | 1447 | 1416 |
Instruction Following Too close to call
Grok 4.20 Multi-Agent: 74.8 (#84), MiMo-V2.5: 75.5 (#60)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1434 |
Long Context Too close to call
Grok 4.20 Multi-Agent: 43.7 (#88), MiMo-V2.5: 44.2 (#73)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1431 | 1445 |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.0 (#59), MiMo-V2.5: 61.6 (#86)
| Benchmark | Grok 4.20 Multi-Agent | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1450 | 1428 |
| LMArena Creative Writing | 1436 | 1393 |
| LMArena Multi-Turn | 1452 | 1445 |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than MiMo-V2.5?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 43.4 on the Noometry Index. MiMo-V2.5 costs 8.9× less per token, which makes it the better buy when Grok 4.20 Multi-Agent's lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 Multi-Agent or MiMo-V2.5?
MiMo-V2.5 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-V2.5 better for coding?
They score almost the same on coding (43.0 vs 43.9); test both on your own repository before choosing.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 1M.
How many benchmarks do Grok 4.20 Multi-Agent and MiMo-V2.5 share?
18 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and MiMo-V2.5 has 23.