Model comparison
Amazon Nova Pro vs Granite 4.2 8B
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 31.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Granite 4.2 8B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 8B leads 38.4 to 27.4.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 131K.
- Granite 4.2 8B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Granite 4.2 8B | |
|---|---|---|
| Provider | Amazon | IBM |
| Noometry Index | 31.0 | 40.5 |
| Released | 2024-12-03 | — |
| Weights | Proprietary | Open |
| Context window | 300K | 131K |
| Max output | 10K | 118K |
| Input $ / M tokens | $0.80 | $0.06 |
| Output $ / M tokens | $3.20 | $0.25 |
| Results tracked | 38 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 8B leads
Amazon Nova Pro: 35.1 (#229), Granite 4.2 8B: 40.5 (#137)
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Coding | 1270 | 1380 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Granite 4.2 8B: —
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Granite 4.2 8B leads
Amazon Nova Pro: 20.0 (#243), Granite 4.2 8B: 26.6 (#131)
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1329 |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math Not comparable
Amazon Nova Pro: 28.5 (#243), Granite 4.2 8B: —
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| LMArena Math | 1252 | — |
Knowledge Granite 4.2 8B leads
Amazon Nova Pro: 27.4 (#250), Granite 4.2 8B: 38.4 (#145)
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Expert | 1211 | 1384 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Granite 4.2 8B: —
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Granite 4.2 8B leads
Amazon Nova Pro: 39.7 (#223), Granite 4.2 8B: 44.5 (#178)
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Non-English | 1234 | 1302 |
| LMArena Chinese | 1244 | 1366 |
| LMArena Russian | 1240 | 1285 |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1182 | — |
Instruction Following Granite 4.2 8B leads
Amazon Nova Pro: 64.9 (#226), Granite 4.2 8B: 68.7 (#184)
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1301 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Granite 4.2 8B leads
Amazon Nova Pro: 38.1 (#205), Granite 4.2 8B: 40.3 (#159)
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Longer Query | 1255 | 1324 |
Writing & Preference Granite 4.2 8B leads
Amazon Nova Pro: 43.9 (#226), Granite 4.2 8B: 49.6 (#189)
| Benchmark | Amazon Nova Pro | Granite 4.2 8B |
|---|---|---|
| LMArena Text | 1259 | 1320 |
| LMArena Creative Writing | 1212 | 1236 |
| LMArena Multi-Turn | 1246 | 1301 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Granite 4.2 8B?
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Granite 4.2 8B?
Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Granite 4.2 8B better for coding?
Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 131K.
How many benchmarks do Amazon Nova Pro and Granite 4.2 8B share?
11 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Granite 4.2 8B has 11.