Model comparison
Llama 3-8B vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
UpstageSummary
- They share 17 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Solar Pro4 leads 39.8 to 7.8.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | Solar Pro4 | |
|---|---|---|
| Provider | Meta | Upstage |
| Noometry Index | 25.5 | 42.1 |
| Released | 2024-04-18 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | — | 524K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Llama 3-8B: 31.0 (#289), Solar Pro4: 40.1 (#149)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1152 | 1437 |
| LMArena WebDev | — | 1371 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Solar Pro4 leads
Llama 3-8B: 14.3 (#326), Solar Pro4: 28.5 (#104)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1399 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Solar Pro4 leads
Llama 3-8B: 8.8 (#323), Solar Pro4: 38.8 (#128)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Math | 1151 | 1416 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Solar Pro4 leads
Llama 3-8B: 7.8 (#308), Solar Pro4: 39.8 (#129)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1113 | 1427 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Solar Pro4 leads
Llama 3-8B: 30.8 (#261), Solar Pro4: 48.7 (#139)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1098 | 1361 |
| LMArena Chinese | 1076 | 1415 |
| LMArena French | 1159 | 1397 |
| LMArena German | 1104 | 1364 |
| LMArena Japanese | 967 | 1309 |
| LMArena Korean | 1004 | 1382 |
| LMArena Russian | 1109 | 1360 |
| LMArena Spanish | 1173 | 1401 |
Instruction Following Solar Pro4 leads
Llama 3-8B: 58.4 (#260), Solar Pro4: 72.7 (#132)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1377 |
Long Context Solar Pro4 leads
Llama 3-8B: 34.2 (#251), Solar Pro4: 42.1 (#130)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1128 | 1381 |
Writing & Preference Solar Pro4 leads
Llama 3-8B: 37.5 (#256), Solar Pro4: 56.5 (#138)
| Benchmark | Llama 3-8B | Solar Pro4 |
|---|---|---|
| LMArena Text | 1166 | 1386 |
| LMArena Creative Writing | 1150 | 1316 |
| LMArena Multi-Turn | 1152 | 1385 |
Frequently asked questions
Is Llama 3-8B better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 25.5 on the Noometry Index.
Is Llama 3-8B or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Solar Pro4 share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Solar Pro4 has 18.