Model comparison
gpt-oss-20b vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 15× less per token, which makes it the better buy when Solar Pro4's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
UpstageSummary
- They share 16 benchmarks with published results for both. gpt-oss-20b scores higher in 1 category and Solar Pro4 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Solar Pro4 leads 56.5 to 35.5.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
- Solar Pro4 accepts more context: 524K tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Solar Pro4 | |
|---|---|---|
| Provider | OpenAI | Upstage |
| Noometry Index | 32.5 | 42.1 |
| Released | 2025-08-05 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 131K | 524K |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.018 | $0.30 |
| Output $ / M tokens | $0.09 | $1.20 |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
gpt-oss-20b: 37.6 (#192), Solar Pro4: 40.1 (#149)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1306 | 1437 |
| LMArena WebDev | — | 1371 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Solar Pro4: —
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Solar Pro4 leads
gpt-oss-20b: 19.3 (#261), Solar Pro4: 28.5 (#104)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1399 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math Too close to call
gpt-oss-20b: 39.4 (#103), Solar Pro4: 38.8 (#128)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Math | 1317 | 1416 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge Solar Pro4 leads
gpt-oss-20b: 34.6 (#195), Solar Pro4: 39.8 (#129)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1258 | 1427 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Solar Pro4 leads
gpt-oss-20b: 42.2 (#197), Solar Pro4: 48.7 (#139)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1268 | 1361 |
| LMArena Chinese | 1314 | 1415 |
| LMArena German | 1255 | 1364 |
| LMArena Japanese | 1244 | 1309 |
| LMArena Korean | 1236 | 1382 |
| LMArena Russian | 1278 | 1360 |
| LMArena Spanish | 1267 | 1401 |
| LMArena French | — | 1397 |
Instruction Following Solar Pro4 leads
gpt-oss-20b: 61.8 (#240), Solar Pro4: 72.7 (#132)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1377 |
| IFEval | 73.2% | — |
Long Context Solar Pro4 leads
gpt-oss-20b: 37.9 (#209), Solar Pro4: 42.1 (#130)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1250 | 1381 |
Writing & Preference Solar Pro4 leads
gpt-oss-20b: 35.5 (#265), Solar Pro4: 56.5 (#138)
| Benchmark | gpt-oss-20b | Solar Pro4 |
|---|---|---|
| LMArena Text | 1287 | 1386 |
| LMArena Creative Writing | 1201 | 1316 |
| LMArena Multi-Turn | 1268 | 1385 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 15× less per token, which makes it the better buy when Solar Pro4's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Solar Pro4?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.
Is gpt-oss-20b or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 131K.
How many benchmarks do gpt-oss-20b and Solar Pro4 share?
16 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Solar Pro4 has 18.