Model comparison
GPT-4.5 vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 37.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
UpstageSummary
- They share 16 benchmarks with published results for both. GPT-4.5 scores higher in 3 categories and Solar Pro4 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Solar Pro4 leads 28.5 to 13.9.
Side by side
| GPT-4.5 | Solar Pro4 | |
|---|---|---|
| Provider | OpenAI | Upstage |
| Noometry Index | 37.2 | 42.1 |
| Released | 2025-02-27 | 2026-08-06 |
| Weights | Proprietary | Proprietary |
| Context window | — | 524K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 42 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 42.2 (#109), Solar Pro4: 40.1 (#149)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1396 | 1437 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1371 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Solar Pro4: —
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Solar Pro4 leads
GPT-4.5: 13.9 (#330), Solar Pro4: 28.5 (#104)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1399 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Solar Pro4 leads
GPT-4.5: 32.6 (#211), Solar Pro4: 38.8 (#128)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1412 | 1416 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Solar Pro4 leads
GPT-4.5: 32.5 (#211), Solar Pro4: 39.8 (#129)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1394 | 1427 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal Not comparable
GPT-4.5: 37.6 (#71), Solar Pro4: —
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.5 (#83), Solar Pro4: 48.7 (#139)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1413 | 1361 |
| LMArena Chinese | 1421 | 1415 |
| LMArena French | 1418 | 1397 |
| LMArena German | 1457 | 1364 |
| LMArena Japanese | 1416 | 1309 |
| LMArena Korean | 1392 | 1382 |
| LMArena Russian | 1419 | 1360 |
| LMArena Spanish | — | 1401 |
Instruction Following Too close to call
GPT-4.5: 72.6 (#134), Solar Pro4: 72.7 (#132)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1377 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Solar Pro4 leads
GPT-4.5: 40.4 (#155), Solar Pro4: 42.1 (#130)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1406 | 1381 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Too close to call
GPT-4.5: 56.9 (#134), Solar Pro4: 56.5 (#138)
| Benchmark | GPT-4.5 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1417 | 1386 |
| LMArena Creative Writing | 1394 | 1316 |
| LMArena Multi-Turn | 1444 | 1385 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 37.2 on the Noometry Index.
Is GPT-4.5 or Solar Pro4 better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 40.1 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Solar Pro4 share?
16 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Solar Pro4 has 18.