Model comparison
Grok 4.20 Multi-Agent vs Magistral Medium
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 35.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 8.6.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 Multi-Agent | Magistral Medium | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 46.2 | 35.2 |
| Released | 2026-03-09 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 30K | 16K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $2.50 | $5 |
| Results tracked | 20 | 22 |
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), Magistral Medium: 39.1 (#161)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Coding | 1457 | 1319 |
| SciCode | — | 39.2% |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, Magistral Medium: —
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Search | 1204 | — |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.9 (#48), Magistral Medium: 8.6 (#348)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
Math Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 39.4 (#104), Magistral Medium: 35.1 (#189)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Math | 1442 | 1250 |
Knowledge Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 40.4 (#119), Magistral Medium: 33.5 (#202)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Expert | 1445 | 1223 |
Multimodal Not comparable
Grok 4.20 Multi-Agent: 40.5 (#48), Magistral Medium: —
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Vision | 1259 | — |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 54.4 (#43), Magistral Medium: 39.6 (#224)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1440 | 1232 |
| LMArena Chinese | 1475 | 1227 |
| LMArena French | 1466 | 1267 |
| LMArena German | 1456 | 1248 |
| LMArena Japanese | 1405 | 1175 |
| LMArena Korean | 1416 | 1125 |
| LMArena Russian | 1457 | 1224 |
| LMArena Spanish | 1447 | 1271 |
Instruction Following Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 74.8 (#84), Magistral Medium: 66.0 (#211)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1420 | 1254 |
Long Context Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.7 (#88), Magistral Medium: 39.3 (#183)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1431 | 1295 |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.0 (#59), Magistral Medium: 46.3 (#219)
| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Text | 1450 | 1255 |
| LMArena Creative Writing | 1436 | 1245 |
| LMArena Multi-Turn | 1452 | 1275 |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than Magistral Medium?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 35.2 on the Noometry Index.
Which is cheaper, Grok 4.20 Multi-Agent or Magistral Medium?
Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Magistral Medium lists at $2 and $5.
Is Grok 4.20 Multi-Agent or Magistral Medium better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 Multi-Agent does, with 1M tokens against 262K.
How many benchmarks do Grok 4.20 Multi-Agent and Magistral Medium share?
17 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Magistral Medium has 22.