Model comparison
Gemini 3 Deep Think vs Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent has enough public results to be ranked (#65); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
GoogleSummary
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 43.9.
Side by side
| Gemini 3 Deep Think | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 58.3 | 46.2 |
| Released | 2026-02-12 | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 3 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 43.0 (#92)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | — | 1457 |
Agentic & Tool Use Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: —
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | — | 1204 |
Reasoning Gemini 3 Deep Think leads
Gemini 3 Deep Think: 70.2 (#14), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| ARC-AGI-2 | 84.6% | — |
| NYT Connections (extended) | — | 89.6% |
| ARC-AGI-1 | 96% | — |
| CritPt | 25.7% | — |
| LMArena Hard Prompts | — | 1448 |
Math Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | — | 1442 |
Knowledge Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | — | 1445 |
Multimodal Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | — | 1440 |
| LMArena Chinese | — | 1475 |
| LMArena French | — | 1466 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1416 |
| LMArena Russian | — | 1457 |
| LMArena Spanish | — | 1447 |
Instruction Following Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | — | 1420 |
Long Context Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | — | 1431 |
Writing & Preference Not comparable
Gemini 3 Deep Think: —, Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | Gemini 3 Deep Think | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | — | 1450 |
| LMArena Creative Writing | — | 1436 |
| LMArena Multi-Turn | — | 1452 |
Frequently asked questions
Is Gemini 3 Deep Think better than Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent has enough public results to be ranked (#65); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Gemini 3 Deep Think and Grok 4.20 Multi-Agent share?
0 benchmarks have published results for both models. Gemini 3 Deep Think has 3 scored results on Noometry and Grok 4.20 Multi-Agent has 20.