Model comparison
Amazon Nova Pro vs Grok-2 (Dec 2024)
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 31.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Amazon Nova Pro scores higher in 3 categories and Grok-2 (Dec 2024) in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 20.8.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.6% for Amazon Nova Pro and 54.8% for Grok-2 (Dec 2024).
Side by side
| Amazon Nova Pro | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Amazon | xAI |
| Noometry Index | 31.0 | 33.7 |
| Released | 2024-12-03 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Coding | 38.1% | 46.4% |
| LMArena Coding | 1270 | 1287 |
| WeirdML | — | 22.2% |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Grok-2 (Dec 2024): —
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Reasoning | 32.6% | 54.8% |
| LMArena Hard Prompts | 1246 | 1272 |
| LiveBench Data Analysis | 48.3% | 54.5% |
| Epoch Capabilities Index | 123.8 | 130.48 |
| LiveBench | 43.5% | 54.3% |
| SimpleBench | — | 22.7% |
| DTBench | — | 65.2% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Math | 38% | 54.9% |
| LMArena Math | 1252 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 11.5% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Grok-2 (Dec 2024) leads
Amazon Nova Pro: 27.4 (#250), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| Confabulations | 30.1% | 20.1% |
| LMArena Expert | 1211 | 1254 |
| GPQA Diamond | — | 53.8% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Grok-2 (Dec 2024): —
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Grok-2 (Dec 2024) leads
Amazon Nova Pro: 39.7 (#223), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1234 | 1282 |
| LMArena Chinese | 1244 | 1289 |
| LMArena French | 1271 | 1318 |
| LMArena German | 1243 | 1287 |
| LMArena Japanese | 1200 | 1244 |
| LMArena Korean | 1203 | 1237 |
| LMArena Russian | 1240 | 1286 |
| LMArena Spanish | 1182 | 1281 |
Instruction Following Grok-2 (Dec 2024) leads
Amazon Nova Pro: 64.9 (#226), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 69.6% |
| LMArena Instruction Following | 1235 | 1270 |
| IFEval | 81.5% | — |
Long Context Too close to call
Amazon Nova Pro: 38.1 (#205), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1255 | 1276 |
Writing & Preference Grok-2 (Dec 2024) leads
Amazon Nova Pro: 43.9 (#226), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | Amazon Nova Pro | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1259 | 1305 |
| LMArena Creative Writing | 1212 | 1284 |
| Short-Story Creative Writing | 60.5% | 63.6% |
| LMArena Multi-Turn | 1246 | 1290 |
| LiveBench Language | 37% | 45.6% |
| WildBench | 77.7% | — |
Frequently asked questions
Is Amazon Nova Pro better than Grok-2 (Dec 2024)?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or Grok-2 (Dec 2024) better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 33.3 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Grok-2 (Dec 2024) share?
27 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Grok-2 (Dec 2024) has 34.