Model comparison
Phi 3 Small 8k Instruct vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 41.5 to 28.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
UpstageSummary
- They share 17 benchmarks with published results for both. Phi 3 Small 8k 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 56.7 to 31.3.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Small 8k Instruct | Solar Pro4 | |
|---|---|---|
| Provider | Microsoft | Upstage |
| Noometry Index | 28.8 | 41.5 |
| Released | 2024-04-23 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | — | 524K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 32 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Phi 3 Small 8k Instruct: 27.4 (#313), Solar Pro4: 39.9 (#135)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1102 | 1439 |
| LMArena WebDev | — | 1371 |
| LiveBench Coding | 20.3% | — |
Reasoning Solar Pro4 leads
Phi 3 Small 8k Instruct: 14.2 (#319), Solar Pro4: 27.3 (#107)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1398 |
| LiveBench Reasoning | 15.9% | — |
| LiveBench Data Analysis | 30.3% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |
Math Solar Pro4 leads
Phi 3 Small 8k Instruct: 25.4 (#247), Solar Pro4: 36.1 (#129)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Math | 1151 | 1418 |
| LiveBench Math | 17.6% | — |
Knowledge Solar Pro4 leads
Phi 3 Small 8k Instruct: 28.5 (#237), Solar Pro4: 39.0 (#128)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1067 | 1421 |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Solar Pro4 leads
Phi 3 Small 8k Instruct: 28.6 (#267), Solar Pro4: 49.0 (#134)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1058 | 1362 |
| LMArena Chinese | 1061 | 1417 |
| LMArena French | 1134 | 1403 |
| LMArena German | 1080 | 1351 |
| LMArena Japanese | 966 | 1300 |
| LMArena Korean | 894 | 1383 |
| LMArena Russian | 1111 | 1360 |
| LMArena Spanish | 1111 | 1408 |
Instruction Following Solar Pro4 leads
Phi 3 Small 8k Instruct: 52.2 (#287), Solar Pro4: 72.8 (#128)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1087 | 1376 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Solar Pro4 leads
Phi 3 Small 8k Instruct: 33.0 (#262), Solar Pro4: 42.0 (#125)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1088 | 1379 |
Writing & Preference Solar Pro4 leads
Phi 3 Small 8k Instruct: 31.3 (#279), Solar Pro4: 56.7 (#133)
| Benchmark | Phi 3 Small 8k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Text | 1110 | 1386 |
| LMArena Creative Writing | 1083 | 1313 |
| LMArena Multi-Turn | 1068 | 1391 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 41.5 to 28.8 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 39.9 versus 27.4 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Solar Pro4 share?
17 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Solar Pro4 has 18.