Model comparison
Phi 3 Mini 4k Instruct vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
UpstageSummary
- They share 17 benchmarks with published results for both. Phi 3 Mini 4k 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 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Mini 4k Instruct | Solar Pro4 | |
|---|---|---|
| Provider | Microsoft | Upstage |
| Noometry Index | 27.9 | 42.1 |
| 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 | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Solar Pro4: 40.1 (#149)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1093 | 1437 |
| LMArena WebDev | — | 1371 |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Solar Pro4 leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Solar Pro4: 28.5 (#104)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1399 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Solar Pro4 leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Solar Pro4: 38.8 (#128)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Math | 1111 | 1416 |
| LiveBench Math | 15.7% | — |
Knowledge Solar Pro4 leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Solar Pro4: 39.8 (#129)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1045 | 1427 |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Solar Pro4 leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Solar Pro4: 48.7 (#139)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1021 | 1361 |
| LMArena Chinese | 1021 | 1415 |
| LMArena French | 1076 | 1397 |
| LMArena German | 1044 | 1364 |
| LMArena Japanese | 935 | 1309 |
| LMArena Korean | 905 | 1382 |
| LMArena Russian | 1022 | 1360 |
| LMArena Spanish | 1085 | 1401 |
Instruction Following Solar Pro4 leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Solar Pro4: 72.7 (#132)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1053 | 1377 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Solar Pro4 leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Solar Pro4: 42.1 (#130)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1044 | 1381 |
Writing & Preference Solar Pro4 leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Solar Pro4: 56.5 (#138)
| Benchmark | Phi 3 Mini 4k Instruct | Solar Pro4 |
|---|---|---|
| LMArena Text | 1073 | 1386 |
| LMArena Creative Writing | 1037 | 1316 |
| LMArena Multi-Turn | 1018 | 1385 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Solar Pro4 share?
17 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Solar Pro4 has 18.