Model comparison
Granite 4.2 3b vs Nova Premier 1.0
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 37.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in writing & preference, where Nova Premier 1.0 leads 51.0 to 47.9.
- Granite 4.2 3b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.2 3b | Nova Premier 1.0 | |
|---|---|---|
| Provider | IBM | Amazon |
| Noometry Index | 39.0 | 37.7 |
| Released | — | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 10K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $12.50 |
| Results tracked | 11 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.2 3b: 39.4 (#146), Nova Premier 1.0: —
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| LMArena Coding | 1363 | — |
Reasoning Granite 4.2 3b leads
Granite 4.2 3b: 25.0 (#136), Nova Premier 1.0: 22.3 (#182)
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| LMArena Hard Prompts | 1308 | — |
Math Not comparable
Granite 4.2 3b: —, Nova Premier 1.0: 31.5 (#194)
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | — | 35% |
Knowledge Too close to call
Granite 4.2 3b: 35.6 (#169), Nova Premier 1.0: 35.4 (#176)
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1313 | — |
Multilingual Not comparable
Granite 4.2 3b: 42.4 (#193), Nova Premier 1.0: —
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1268 | — |
| LMArena Russian | 1249 | — |
Instruction Following Too close to call
Granite 4.2 3b: 67.2 (#195), Nova Premier 1.0: 66.9 (#201)
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1271 | — |
Long Context Not comparable
Granite 4.2 3b: 39.3 (#179), Nova Premier 1.0: —
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1293 | — |
Writing & Preference Nova Premier 1.0 leads
Granite 4.2 3b: 47.9 (#202), Nova Premier 1.0: 51.0 (#174)
| Benchmark | Granite 4.2 3b | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1295 | — |
| LMArena Creative Writing | 1215 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1293 | — |
Frequently asked questions
Is Granite 4.2 3b better than Nova Premier 1.0?
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 37.7 on the Noometry Index.
How many benchmarks do Granite 4.2 3b and Nova Premier 1.0 share?
0 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Nova Premier 1.0 has 6.