Model comparison
o3 vs Solar Pro4
o3 is the stronger model overall, scoring 47.5 to 42.1 on the Noometry Index. Solar Pro4 costs 6.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
UpstageSummary
- They share 17 benchmarks with published results for both. o3 scores higher in 8 categories and Solar Pro4 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 39.8.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $8 for o3.
- Solar Pro4 accepts more context: 524K tokens versus 200K.
Side by side
| o3 | Solar Pro4 | |
|---|---|---|
| Provider | OpenAI | Upstage |
| Noometry Index | 47.5 | 42.1 |
| Released | 2025-04-16 | 2026-08-06 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 524K |
| Max output | 100K | 131K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $8 | $1.20 |
| Results tracked | 63 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Solar Pro4: 40.1 (#149)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1408 | 1437 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| LMArena WebDev | — | 1371 |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Solar Pro4: —
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning o3 leads
o3: 32.0 (#78), Solar Pro4: 28.5 (#104)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1402 | 1399 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 60.8% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 38% | — |
| EnigmaEval | 13.1% | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 84.8% | — |
| LMCA | 39.7% | — |
| Epoch Capabilities Index | 146.86 | — |
| ForecastBench | 62.5 | — |
Math o3 leads
o3: 50.2 (#58), Solar Pro4: 38.8 (#128)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1426 | 1416 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| Omni-MATH | 71.4% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge o3 leads
o3: 54.6 (#52), Solar Pro4: 39.8 (#129)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1402 | 1427 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |
Multimodal Not comparable
o3: 41.4 (#36), Solar Pro4: —
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual o3 leads
o3: 51.7 (#105), Solar Pro4: 48.7 (#139)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1401 | 1361 |
| LMArena Chinese | 1437 | 1415 |
| LMArena French | 1430 | 1397 |
| LMArena German | 1420 | 1364 |
| LMArena Japanese | 1403 | 1309 |
| LMArena Korean | 1370 | 1382 |
| LMArena Russian | 1406 | 1360 |
| LMArena Spanish | 1395 | 1401 |
Instruction Following Too close to call
o3: 72.8 (#127), Solar Pro4: 72.7 (#132)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1368 | 1377 |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Solar Pro4: 42.1 (#130)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1372 | 1381 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference o3 leads
o3: 63.5 (#64), Solar Pro4: 56.5 (#138)
| Benchmark | o3 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1410 | 1386 |
| LMArena Creative Writing | 1359 | 1316 |
| LMArena Multi-Turn | 1405 | 1385 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
Frequently asked questions
Is o3 better than Solar Pro4?
o3 is the stronger model overall, scoring 47.5 to 42.1 on the Noometry Index. Solar Pro4 costs 6.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, o3 or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; o3 lists at $2 and $8.
Is o3 or Solar Pro4 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 200K.
How many benchmarks do o3 and Solar Pro4 share?
17 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Solar Pro4 has 18.