Model comparison
Grok 4.20 Multi-Agent vs MiniMax-M2.7
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 3.0× 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.
MiniMaxSummary
- They share 18 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and MiniMax-M2.7 in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 19.7.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for Grok 4.20 Multi-Agent and 24.7% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 Multi-Agent | MiniMax-M2.7 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 46.2 | 37.7 |
| Released | 2026-03-09 | 2026-03-18 |
| Weights | Proprietary | Open |
| Context window | 1M | 205K |
| Max output | 30K | 131K |
| Input $ / M tokens | $1.25 | $0.30 |
| Output $ / M tokens | $2.50 | $1.20 |
| Results tracked | 20 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.0 (#92), MiniMax-M2.7: 41.8 (#120)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1457 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, MiniMax-M2.7: 25.1 (#111)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
| LMArena Search | 1204 | — |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.9 (#48), MiniMax-M2.7: 19.7 (#253)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| NYT Connections (extended) | 89.6% | 24.7% |
| LMArena Hard Prompts | 1448 | 1422 |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.85 |
Math Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 39.4 (#104), MiniMax-M2.7: 25.9 (#263)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1442 | 1420 |
| ProofBench | — | 3% |
Knowledge Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 40.4 (#119), MiniMax-M2.7: 37.7 (#152)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1445 | 1444 |
| Vectara Hallucination Rate | — | 12.9% |
Multimodal Not comparable
Grok 4.20 Multi-Agent: 40.5 (#48), MiniMax-M2.7: —
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1259 | — |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 54.4 (#43), MiniMax-M2.7: 50.3 (#123)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1440 | 1382 |
| LMArena Chinese | 1475 | 1441 |
| LMArena French | 1466 | 1421 |
| LMArena German | 1456 | 1398 |
| LMArena Japanese | 1405 | 1262 |
| LMArena Korean | 1416 | 1313 |
| LMArena Russian | 1457 | 1383 |
| LMArena Spanish | 1447 | 1403 |
Instruction Following Too close to call
Grok 4.20 Multi-Agent: 74.8 (#84), MiniMax-M2.7: 74.1 (#103)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1405 |
Long Context Too close to call
Grok 4.20 Multi-Agent: 43.7 (#88), MiniMax-M2.7: 43.3 (#99)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1431 | 1419 |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.0 (#59), MiniMax-M2.7: 58.9 (#112)
| Benchmark | Grok 4.20 Multi-Agent | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1450 | 1405 |
| LMArena Creative Writing | 1436 | 1354 |
| LMArena Multi-Turn | 1452 | 1412 |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than MiniMax-M2.7?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 3.0× 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 MiniMax-M2.7?
MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.
Is Grok 4.20 Multi-Agent or MiniMax-M2.7 better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 Multi-Agent does, with 1M tokens against 205K.
How many benchmarks do Grok 4.20 Multi-Agent and MiniMax-M2.7 share?
18 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and MiniMax-M2.7 has 30.