Model comparison
Amazon Nova Pro vs Granite 3.1 2b Instruct
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 31.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Amazon Nova Pro scores higher in 5 categories and Granite 3.1 2b Instruct in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Amazon Nova Pro leads 39.7 to 29.1.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Amazon | IBM |
| Noometry Index | 31.0 | 33.2 |
| Released | 2024-12-03 | — |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 12 |
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), Granite 3.1 2b Instruct: 33.4 (#257)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1270 | 1149 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Granite 3.1 2b Instruct: —
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Granite 3.1 2b Instruct leads
Amazon Nova Pro: 20.0 (#243), Granite 3.1 2b Instruct: 22.0 (#209)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1138 |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math Granite 3.1 2b Instruct leads
Amazon Nova Pro: 28.5 (#243), Granite 3.1 2b Instruct: 33.1 (#206)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1252 | 1159 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Granite 3.1 2b Instruct leads
Amazon Nova Pro: 27.4 (#250), Granite 3.1 2b Instruct: 30.8 (#224)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1211 | 1131 |
| 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 3.1 2b Instruct: —
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Granite 3.1 2b Instruct: 29.1 (#269)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1234 | 1068 |
| LMArena Chinese | 1244 | 1139 |
| LMArena Russian | 1240 | 1063 |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1182 | — |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Granite 3.1 2b Instruct: 57.7 (#264)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1235 | 1116 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Granite 3.1 2b Instruct: 35.0 (#244)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1255 | 1155 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Granite 3.1 2b Instruct: 34.1 (#274)
| Benchmark | Amazon Nova Pro | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1259 | 1127 |
| LMArena Creative Writing | 1212 | 1116 |
| LMArena Multi-Turn | 1246 | 1099 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Granite 3.1 2b Instruct?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or Granite 3.1 2b Instruct better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 33.4 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Granite 3.1 2b Instruct has 12.