Model comparison
GPT-4 vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
UpstageSummary
- They share 17 benchmarks with published results for both. GPT-4 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 10.8.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $30 / $60 for GPT-4.
- Solar Pro4 accepts more context: 524K tokens versus 8K.
Side by side
| GPT-4 | Solar Pro4 | |
|---|---|---|
| Provider | OpenAI | Upstage |
| Noometry Index | 29.1 | 42.1 |
| Released | 2023-03-14 | 2026-08-06 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | 524K |
| Max output | 8K | 131K |
| Input $ / M tokens | $30 | $0.30 |
| Output $ / M tokens | $60 | $1.20 |
| Results tracked | 38 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
GPT-4: 31.6 (#283), Solar Pro4: 40.1 (#149)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1254 | 1437 |
| LMArena WebDev | — | 1371 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Solar Pro4: —
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Solar Pro4 leads
GPT-4: 17.8 (#289), Solar Pro4: 28.5 (#104)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1399 |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Solar Pro4 leads
GPT-4: 10.8 (#309), Solar Pro4: 38.8 (#128)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1269 | 1416 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Solar Pro4 leads
GPT-4: 18.4 (#282), Solar Pro4: 39.8 (#129)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1211 | 1427 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Solar Pro4 leads
GPT-4: 40.6 (#215), Solar Pro4: 48.7 (#139)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1246 | 1361 |
| LMArena Chinese | 1242 | 1415 |
| LMArena French | 1283 | 1397 |
| LMArena German | 1251 | 1364 |
| LMArena Japanese | 1209 | 1309 |
| LMArena Korean | 1184 | 1382 |
| LMArena Russian | 1251 | 1360 |
| LMArena Spanish | 1261 | 1401 |
Instruction Following Solar Pro4 leads
GPT-4: 65.3 (#222), Solar Pro4: 72.7 (#132)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1377 |
Long Context Solar Pro4 leads
GPT-4: 37.7 (#212), Solar Pro4: 42.1 (#130)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1244 | 1381 |
Writing & Preference Solar Pro4 leads
GPT-4: 34.9 (#268), Solar Pro4: 56.5 (#138)
| Benchmark | GPT-4 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1263 | 1386 |
| LMArena Creative Writing | 1244 | 1316 |
| LMArena Multi-Turn | 1257 | 1385 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-4 lists at $30 and $60.
Is GPT-4 or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 8K.
How many benchmarks do GPT-4 and Solar Pro4 share?
17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Solar Pro4 has 18.