# Llama 3-70B vs Solar Pro4

> Solar Pro4 is the stronger model overall, scoring 42.1 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-70b-vs-solar-pro4
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Solar Pro4 leads 38.8 to 12.8.
- Llama 3-70B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 3-70B | Solar Pro4 |
|---|---|---|
| Provider | Meta | Upstage |
| Noometry Index | 28.8 | 42.1 |
| Rank | 323 | 121 |
| Context | — | 524K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Proprietary |

## Coding

- Llama 3-70B: 35.8 (#218)
- Solar Pro4: 40.1 (#149)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1206 | 1437 |
| LMArena WebDev | — | 1371 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |

## Agentic & Tool Use

- Llama 3-70B: 21.1 (#139)
- Solar Pro4: —

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| Cybench | 5% | — |

## Reasoning

- Llama 3-70B: 18.0 (#288)
- Solar Pro4: 28.5 (#104)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1399 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |

## Math

- Llama 3-70B: 12.8 (#305)
- Solar Pro4: 38.8 (#128)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Math | 1218 | 1416 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |

## Knowledge

- Llama 3-70B: 20.8 (#277)
- Solar Pro4: 39.8 (#129)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1149 | 1427 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |

## Multilingual

- Llama 3-70B: 33.6 (#251)
- Solar Pro4: 48.7 (#139)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1142 | 1361 |
| LMArena Chinese | 1114 | 1415 |
| LMArena French | 1232 | 1397 |
| LMArena German | 1169 | 1364 |
| LMArena Japanese | 1017 | 1309 |
| LMArena Korean | 1017 | 1382 |
| LMArena Russian | 1159 | 1360 |
| LMArena Spanish | 1241 | 1401 |

## Instruction Following

- Llama 3-70B: 62.5 (#238)
- Solar Pro4: 72.7 (#132)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1194 | 1377 |

## Long Context

- Llama 3-70B: 35.6 (#240)
- Solar Pro4: 42.1 (#130)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1174 | 1381 |

## Writing & Preference

- Llama 3-70B: 42.8 (#231)
- Solar Pro4: 56.5 (#138)

| Benchmark | Llama 3-70B | Solar Pro4 |
|---|---|---|
| LMArena Text | 1221 | 1386 |
| LMArena Creative Writing | 1210 | 1316 |
| LMArena Multi-Turn | 1223 | 1385 |

## FAQ

### Is Llama 3-70B better than Solar Pro4?

Solar Pro4 is the stronger model overall, scoring 42.1 to 28.8 on the Noometry Index.

### Is Llama 3-70B or Solar Pro4 better for coding?

Solar Pro4 scores higher on coding benchmarks: 40.1 versus 35.8 in the Noometry coding category.

### How many benchmarks do Llama 3-70B and Solar Pro4 share?

17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Solar Pro4 has 18.