Model comparison
Llama 3.1-70B vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 29.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
UpstageSummary
- They share 17 benchmarks with published results for both. Llama 3.1-70B 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 13.5.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
- Solar Pro4 accepts more context: 524K tokens versus 128K.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-70B | Solar Pro4 | |
|---|---|---|
| Provider | Meta | Upstage |
| Noometry Index | 29.6 | 42.1 |
| Released | 2024-07-23 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 128K | 524K |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.40 | $0.30 |
| Output $ / M tokens | $0.40 | $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
Llama 3.1-70B: 30.3 (#296), Solar Pro4: 40.1 (#149)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1260 | 1437 |
| LMArena WebDev | — | 1371 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Solar Pro4: —
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Solar Pro4 leads
Llama 3.1-70B: 21.6 (#220), Solar Pro4: 28.5 (#104)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1399 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math Solar Pro4 leads
Llama 3.1-70B: 13.5 (#304), Solar Pro4: 38.8 (#128)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Math | 1252 | 1416 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Solar Pro4 leads
Llama 3.1-70B: 24.2 (#269), Solar Pro4: 39.8 (#129)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1209 | 1427 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual Solar Pro4 leads
Llama 3.1-70B: 38.8 (#225), Solar Pro4: 48.7 (#139)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1219 | 1361 |
| LMArena Chinese | 1215 | 1415 |
| LMArena French | 1261 | 1397 |
| LMArena German | 1222 | 1364 |
| LMArena Japanese | 1132 | 1309 |
| LMArena Korean | 1140 | 1382 |
| LMArena Russian | 1234 | 1360 |
| LMArena Spanish | 1253 | 1401 |
Instruction Following Solar Pro4 leads
Llama 3.1-70B: 65.3 (#223), Solar Pro4: 72.7 (#132)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1231 | 1377 |
| IFEval | 82.1% | — |
Long Context Solar Pro4 leads
Llama 3.1-70B: 37.6 (#214), Solar Pro4: 42.1 (#130)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1241 | 1381 |
Writing & Preference Solar Pro4 leads
Llama 3.1-70B: 35.4 (#267), Solar Pro4: 56.5 (#138)
| Benchmark | Llama 3.1-70B | Solar Pro4 |
|---|---|---|
| LMArena Text | 1261 | 1386 |
| LMArena Creative Writing | 1232 | 1316 |
| LMArena Multi-Turn | 1256 | 1385 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 29.6 on the Noometry Index.
Which is cheaper, Llama 3.1-70B or Solar Pro4?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.
Is Llama 3.1-70B or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 128K.
How many benchmarks do Llama 3.1-70B and Solar Pro4 share?
17 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Solar Pro4 has 18.