Model comparison
Granite 3.1 8b Instruct vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.0 to 31.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 0 categories and Nova 2 Lite in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nova 2 Lite leads 54.1 to 35.7.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.1 8b Instruct | Nova 2 Lite | |
|---|---|---|
| Provider | IBM | Amazon |
| Noometry Index | 31.8 | 39.0 |
| Released | — | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 13 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Granite 3.1 8b Instruct: 33.9 (#232), Nova 2 Lite: 40.1 (#131)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1186 | 1386 |
Agentic & Tool Use Too close to call
Granite 3.1 8b Instruct: 23.9 (#113), Nova 2 Lite: 23.9 (#114)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | 27.1% |
Reasoning Nova 2 Lite leads
Granite 3.1 8b Instruct: 21.2 (#204), Nova 2 Lite: 26.4 (#120)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1364 |
Math Nova 2 Lite leads
Granite 3.1 8b Instruct: 30.4 (#210), Nova 2 Lite: 34.8 (#154)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1152 | 1359 |
Knowledge Nova 2 Lite leads
Granite 3.1 8b Instruct: 30.6 (#218), Nova 2 Lite: 42.5 (#88)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1142 | 1360 |
| Vectara Hallucination Rate | — | 5.1% |
Multilingual Nova 2 Lite leads
Granite 3.1 8b Instruct: 31.1 (#255), Nova 2 Lite: 47.3 (#148)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1099 | 1337 |
| LMArena Chinese | 1145 | 1364 |
| LMArena Russian | 1092 | 1343 |
| LMArena French | — | 1381 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1273 |
| LMArena Korean | — | 1284 |
| LMArena Spanish | — | 1372 |
Instruction Following Nova 2 Lite leads
Granite 3.1 8b Instruct: 58.9 (#254), Nova 2 Lite: 70.7 (#156)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1131 | 1335 |
Long Context Nova 2 Lite leads
Granite 3.1 8b Instruct: 35.2 (#236), Nova 2 Lite: 40.6 (#145)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1162 | 1335 |
Writing & Preference Nova 2 Lite leads
Granite 3.1 8b Instruct: 35.7 (#261), Nova 2 Lite: 54.1 (#150)
| Benchmark | Granite 3.1 8b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1150 | 1362 |
| LMArena Creative Writing | 1129 | 1291 |
| LMArena Multi-Turn | 1108 | 1338 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.0 to 31.8 on the Noometry Index.
Is Granite 3.1 8b Instruct or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 33.9 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Nova 2 Lite share?
13 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Nova 2 Lite has 19.