Model comparison
Grok 4.20 Multi-Agent vs Mistral Small 3
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 31.2 on the Noometry Index. Mistral Small 3 costs 27× 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 . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.20 Multi-Agent leads 64.0 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 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 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 Multi-Agent | Mistral Small 3 | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 46.2 | 31.2 |
| Released | 2026-03-09 | 2025-01-30 |
| Weights | Proprietary | Open |
| Context window | 1M | 33K |
| Max output | 30K | 16K |
| Input $ / M tokens | $1.25 | $0.05 |
| Output $ / M tokens | $2.50 | $0.08 |
| Results tracked | 20 | 24 |
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), Mistral Small 3: 36.5 (#207)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1457 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, Mistral Small 3: —
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Search | 1204 | — |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.9 (#48), Mistral Small 3: 18.9 (#273)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1233 |
| NYT Connections (extended) | 89.6% | — |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |
Math Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 39.4 (#104), Mistral Small 3: 16.3 (#295)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1442 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
Knowledge Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 40.4 (#119), Mistral Small 3: 25.1 (#263)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1445 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
Multimodal Not comparable
Grok 4.20 Multi-Agent: 40.5 (#48), Mistral Small 3: —
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1259 | — |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 54.4 (#43), Mistral Small 3: 37.3 (#236)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1440 | 1198 |
| LMArena Chinese | 1475 | 1204 |
| LMArena French | 1466 | 1203 |
| LMArena German | 1456 | 1211 |
| LMArena Japanese | 1405 | 1111 |
| LMArena Korean | 1416 | 1188 |
| LMArena Russian | 1457 | 1216 |
| LMArena Spanish | 1447 | — |
Instruction Following Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 74.8 (#84), Mistral Small 3: 63.7 (#229)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1214 |
Long Context Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.7 (#88), Mistral Small 3: 37.8 (#211)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1431 | 1246 |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.0 (#59), Mistral Small 3: 32.2 (#280)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1450 | 1234 |
| LMArena Creative Writing | 1436 | 1195 |
| LMArena Multi-Turn | 1452 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than Mistral Small 3?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 31.2 on the Noometry Index. Mistral Small 3 costs 27× 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 Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.
Is Grok 4.20 Multi-Agent or Mistral Small 3 better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 Multi-Agent does, with 1M tokens against 33K.
How many benchmarks do Grok 4.20 Multi-Agent and Mistral Small 3 share?
16 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Mistral Small 3 has 24.