Model comparison
Amazon Nova Pro vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 31.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 20.0.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 300K.
Side by side
| Amazon Nova Pro | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | Amazon | xAI |
| Noometry Index | 31.0 | 48.6 |
| Released | 2024-12-03 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1M |
| Max output | 10K | 30K |
| Input $ / M tokens | $0.80 | $1.25 |
| Output $ / M tokens | $3.20 | $2.50 |
| Results tracked | 38 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 35.1 (#229), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Coding | 1270 | 1459 |
| LMArena WebDev | — | 1375 |
| WeirdML | — | 52.3% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,150 |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 16.7 (#147), Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 20.0 (#243), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1451 |
| Epoch Capabilities Index | 123.8 | 151.98 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 90.1% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 38.7% |
| ForecastBench | — | 61.4 |
| LiveBench | 43.5% | — |
Math Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 28.5 (#243), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Math | 1252 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | — | 14% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 27.4 (#250), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Expert | 1211 | 1439 |
| GPQA Diamond | — | 89.3% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 30.2% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 25.0 (#126), Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 980 | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 39.7 (#223), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1234 | 1441 |
| LMArena Chinese | 1244 | 1481 |
| LMArena French | 1271 | 1476 |
| LMArena German | 1243 | 1465 |
| LMArena Japanese | 1200 | 1449 |
| LMArena Korean | 1203 | 1417 |
| LMArena Russian | 1240 | 1458 |
| LMArena Spanish | 1182 | 1443 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 64.9 (#226), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1235 | 1420 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 38.1 (#205), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1255 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Amazon Nova Pro: 43.9 (#226), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | Amazon Nova Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1259 | 1451 |
| LMArena Creative Writing | 1212 | 1438 |
| LMArena Multi-Turn | 1246 | 1456 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1574 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Grok 4.20 (Non-Reasoning)?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Amazon Nova Pro or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 300K.
How many benchmarks do Amazon Nova Pro and Grok 4.20 (Non-Reasoning) share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.