Model comparison
Granite 3.0 8b Instruct vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 31.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
UpstageSummary
- They share 12 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Solar Pro4 leads 56.5 to 31.1.
- Granite 3.0 8b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.0 8b Instruct | Solar Pro4 | |
|---|---|---|
| Provider | IBM | Upstage |
| Noometry Index | 31.6 | 42.1 |
| Released | — | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | — | 524K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 14 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Granite 3.0 8b Instruct: 29.7 (#301), Solar Pro4: 40.1 (#149)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1112 | 1437 |
| LMArena WebDev | — | 1371 |
| BigCodeBench Instruct | 29.3% | — |
| BigCodeBench Complete | 35.4% | — |
Reasoning Solar Pro4 leads
Granite 3.0 8b Instruct: 20.9 (#230), Solar Pro4: 28.5 (#104)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1092 | 1399 |
Math Solar Pro4 leads
Granite 3.0 8b Instruct: 32.8 (#210), Solar Pro4: 38.8 (#128)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Math | 1143 | 1416 |
Knowledge Solar Pro4 leads
Granite 3.0 8b Instruct: 29.6 (#236), Solar Pro4: 39.8 (#129)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1087 | 1427 |
Multilingual Solar Pro4 leads
Granite 3.0 8b Instruct: 27.2 (#276), Solar Pro4: 48.7 (#139)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1037 | 1361 |
| LMArena Chinese | 1063 | 1415 |
| LMArena Russian | 1060 | 1360 |
| LMArena French | — | 1397 |
| LMArena German | — | 1364 |
| LMArena Japanese | — | 1309 |
| LMArena Korean | — | 1382 |
| LMArena Spanish | — | 1401 |
Instruction Following Solar Pro4 leads
Granite 3.0 8b Instruct: 56.0 (#276), Solar Pro4: 72.7 (#132)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1088 | 1377 |
Long Context Solar Pro4 leads
Granite 3.0 8b Instruct: 34.0 (#252), Solar Pro4: 42.1 (#130)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1122 | 1381 |
Writing & Preference Solar Pro4 leads
Granite 3.0 8b Instruct: 31.1 (#285), Solar Pro4: 56.5 (#138)
| Benchmark | Granite 3.0 8b Instruct | Solar Pro4 |
|---|---|---|
| LMArena Text | 1096 | 1386 |
| LMArena Creative Writing | 1071 | 1316 |
| LMArena Multi-Turn | 1063 | 1385 |
Frequently asked questions
Is Granite 3.0 8b Instruct better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 31.6 on the Noometry Index.
Is Granite 3.0 8b Instruct or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 29.7 in the Noometry coding category.
How many benchmarks do Granite 3.0 8b Instruct and Solar Pro4 share?
12 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and Solar Pro4 has 18.