Model comparison
Grok 4.20 Multi-Agent vs Nova Premier 1.0
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 38.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 23.0.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
Side by side
| Grok 4.20 Multi-Agent | Nova Premier 1.0 | |
|---|---|---|
| Provider | xAI | Amazon |
| Noometry Index | 46.2 | 38.3 |
| Released | 2026-03-09 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 30K | 10K |
| Input $ / M tokens | $1.25 | $2.50 |
| Output $ / M tokens | $2.50 | $12.50 |
| Results tracked | 20 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok 4.20 Multi-Agent: 43.0 (#92), Nova Premier 1.0: —
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| LMArena Coding | 1457 | — |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, Nova Premier 1.0: —
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| LMArena Search | 1204 | — |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.9 (#48), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| NYT Connections (extended) | 89.6% | — |
| LMArena Hard Prompts | 1448 | — |
Math Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 39.4 (#104), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | — | 35% |
| LMArena Math | 1442 | — |
Knowledge Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 40.4 (#119), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1445 | — |
Multimodal Not comparable
Grok 4.20 Multi-Agent: 40.5 (#48), Nova Premier 1.0: —
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 1259 | — |
Multilingual Not comparable
Grok 4.20 Multi-Agent: 54.4 (#43), Nova Premier 1.0: —
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| 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 Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 74.8 (#84), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1420 | — |
Long Context Not comparable
Grok 4.20 Multi-Agent: 43.7 (#88), Nova Premier 1.0: —
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1431 | — |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.0 (#59), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Grok 4.20 Multi-Agent | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1450 | — |
| LMArena Creative Writing | 1436 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1452 | — |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than Nova Premier 1.0?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 38.3 on the Noometry Index.
Which is cheaper, Grok 4.20 Multi-Agent or Nova Premier 1.0?
Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Grok 4.20 Multi-Agent and Nova Premier 1.0 share?
0 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Nova Premier 1.0 has 6.