gpt-oss-20b vs Solar Pro 4
Solar Pro 4 leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 28.2 to 10.0, and gpt-oss-20b costs 4.0x less per output token ($0.15 vs $0.60 per million). Updated October 21, 2026; 35 benchmarks have a result for both.
gpt-oss-20b or Solar Pro 4: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick gpt-oss-20b for output tokens 4.0x cheaper ($0.15 vs $0.60 per million) and work measured by SciCode or LMArena Text: coding, where it leads.
- Shared results
- 35
- gpt-oss-20b only
- 27
- Solar Pro 4 only
- 10
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Solar Pro 4
Solar Pro 4 leads, 28.2 against 10.0.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only gpt-oss-20b has a GPQA Diamond result, 68.9%.
Directional only
Math
AIME
No call
Only gpt-oss-20b has a AIME result, 86.0%.
Directional only
Knowledge
MMLU Pro
No call
Only gpt-oss-20b has a MMLU Pro result, 71.6%.
Directional only
Web design
Design Arena: websites
Solar Pro 4
Solar Pro 4 leads, 1176 against 852.
Same board, both measured
Long documents
Listed context window
Solar Pro 4
Solar Pro 4 takes 524K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-20b
gpt-oss-20b $0.0001, Solar Pro 4 $0.0004 per turn.
List prices
At a glance
- Coding index
- gpt-oss-20b not benchmarked, Solar Pro 4 not benchmarked.
- Widest category
- Web design, 35.5 points apart on average over 2 shared benchmarks.
- Widest single gap
- Design Arena: websites: gpt-oss-20b 852 against Solar Pro 4 1176, 40.5 points apart on a 0 to 100 scale.
- Output price
- gpt-oss-20b $0.15 against Solar Pro 4 $0.60 per million output tokens, 4.0x apart.
- Context window
- gpt-oss-20b takes 131K tokens, Solar Pro 4 524K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | gpt-oss-20b | Bars | Solar Pro 4 | Ties |
|---|---|---|---|---|
| Coding | 1 | 3 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 2 | ||
| General | 0 | 17 | ||
| All shared boards | 1 | 34 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index13
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1371 | Only Solar Pro 4 measured |
| AA Coding Index | Not measured | 52.7 | Only Solar Pro 4 measured |
| LiveCodeBench (Vals AI) | 80.4% | Not measured | Only gpt-oss-20b measured |
| LiveCodeBench (Artificial Analysis run) | 77.7% | Not measured | Only gpt-oss-20b measured |
| SciCode | 38.9% | 48.0% | Solar Pro 4 |
| Terminal-Bench Hard (Artificial Analysis run) | 10.6% | Not measured | Only gpt-oss-20b measured |
| Terminal-Bench | 3.4% | Not measured | Only gpt-oss-20b measured |
| WeirdML | 40.9% | Not measured | Only gpt-oss-20b measured |
| ALE-Bench | 566.0 | 179.3 | gpt-oss-20b |
| LMArena Text: coding | 1307 | 1438 | Solar Pro 4 |
| LMArena Text: software and IT | 1311 | 1431 | Solar Pro 4 |
| LMArena WebDev: React | Not measured | 1363 | Only Solar Pro 4 measured |
| LMArena WebDev: HTML | Not measured | 1371 | Only Solar Pro 4 measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.0 | 28.2 | Solar Pro 4 |
| Epoch Capabilities Index | 137.7 | Not measured | Only gpt-oss-20b measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1105 | Only Solar Pro 4 measured |
| τ²-Bench Telecom | 60.2% | Not measured | Only gpt-oss-20b measured |
| BrowseComp-Plus | 50.6% | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 68.9% | Not measured | Only gpt-oss-20b measured |
| GPQA Diamond (Artificial Analysis run) | 68.8% | 89.1% | Solar Pro 4 |
| Humanity's Last Exam (Artificial Analysis run) | 11.0% | 29.8% | Solar Pro 4 |
| GPQA Diamond (Epoch AI run) | 60.8% | Not measured | Only gpt-oss-20b measured |
| LMArena Text: hard prompts | 1274 | 1400 | Solar Pro 4 |
| LMArena Text: expert | 1258 | 1428 | Solar Pro 4 |
| LMArena Text: hard prompts in English | 1292 | 1427 | Solar Pro 4 |
| Kagi LLM Benchmark | 53.2% | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| AIME | 86.0% | Not measured | Only gpt-oss-20b measured |
| MATH 500 (Vals AI) | 94.2% | Not measured | Only gpt-oss-20b measured |
| MGSM (Vals AI) | 89.0% | Not measured | Only gpt-oss-20b measured |
| AA Math Index | 89.3 | Not measured | Only gpt-oss-20b measured |
| AIME 2025 (Artificial Analysis run) | 89.3% | Not measured | Only gpt-oss-20b measured |
| OTIS Mock AIME | 65.3% | Not measured | Only gpt-oss-20b measured |
| LMArena Text: math | 1317 | 1421 | Solar Pro 4 |
| LMArena Text: mathematical work | 1305 | 1427 | Solar Pro 4 |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| MMLU Pro | 71.6% | Not measured | Only gpt-oss-20b measured |
| LegalBench (Vals AI) | 70.8% | Not measured | Only gpt-oss-20b measured |
| CaseLaw (Vals AI) | 43.8% | Not measured | Only gpt-oss-20b measured |
| CorpFin (Vals AI) | 53.1% | Not measured | Only gpt-oss-20b measured |
| TaxEval (Vals AI) | 63.7% | Not measured | Only gpt-oss-20b measured |
| MedQA (Vals AI) | 82.9% | Not measured | Only gpt-oss-20b measured |
| MMLU Pro (Artificial Analysis run) | 74.8% | Not measured | Only gpt-oss-20b measured |
| LMArena Text: science | 1296 | 1404 | Solar Pro 4 |
| LMArena Text: medicine and healthcare | 1310 | 1374 | Solar Pro 4 |
| LMArena Text: legal and government | 1280 | 1383 | Solar Pro 4 |
| LMArena Text: business and finance | 1284 | 1381 | Solar Pro 4 |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 852 | 1176 | Solar Pro 4 |
| Design Arena: UI components | Not measured | 1150 | Only Solar Pro 4 measured |
| Design Arena: game dev | Not measured | 1170 | Only Solar Pro 4 measured |
| Design Arena: data viz | 933 | 1177 | Solar Pro 4 |
| Design Arena: 3D | Not measured | 1178 | Only Solar Pro 4 measured |
| Design Arena: all code categories | Not measured | 1182 | Only Solar Pro 4 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| IFBench | 65.1% | Not measured | Only gpt-oss-20b measured |
| Long context reasoning (AA-LCR) | 34.7% | 70.7% | Solar Pro 4 |
| DTBench | 68.0% | Not measured | Only gpt-oss-20b measured |
| LMCA | 14.5% | Not measured | Only gpt-oss-20b measured |
| LMArena Text | 1288 | 1388 | Solar Pro 4 |
| LMArena Text: instruction following | 1236 | 1375 | Solar Pro 4 |
| LMArena Text: creative writing | 1201 | 1317 | Solar Pro 4 |
| LMArena Text: English | 1303 | 1414 | Solar Pro 4 |
| LMArena Text: non-English | 1269 | 1363 | Solar Pro 4 |
| LMArena Text: Chinese | 1315 | 1422 | Solar Pro 4 |
| LMArena Text: German | 1255 | 1358 | Solar Pro 4 |
| LMArena Text: Japanese | 1244 | 1320 | Solar Pro 4 |
| LMArena Text: Korean | 1236 | 1383 | Solar Pro 4 |
| LMArena Text: French | Not measured | 1400 | Only Solar Pro 4 measured |
| LMArena Text: Spanish | 1267 | 1409 | Solar Pro 4 |
| LMArena Text: Russian | 1278 | 1357 | Solar Pro 4 |
| LMArena Text: Polish | 1252 | 1304 | Solar Pro 4 |
| LMArena Text: multi-turn | 1268 | 1385 | Solar Pro 4 |
| LMArena Text: longer queries | 1250 | 1382 | Solar Pro 4 |
| LMArena Text: writing and language | 1238 | 1344 | Solar Pro 4 |
| LMArena Text: entertainment and media | 1216 | 1332 | Solar Pro 4 |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | gpt-oss-20b | Solar Pro 4 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
gpt-oss-20b costs less
Repository review
50K input + 3K output tokens
gpt-oss-20b costs less
Agent loop
200K input + 10K output tokens
gpt-oss-20b costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI gpt-oss-20b | Upstage Solar Pro 4 |
|---|---|---|
| Maker | OpenAI | Upstage |
| Weights | Open weights | No public weights listed |
| Released | August 5, 2025 | August 10, 2026 |
| Context window | 131K | 524K |
| Input $/Mtok | $0.03 | $0.15 |
| Output $/Mtok | $0.15 | $0.60 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is gpt-oss-20b better than Solar Pro 4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 4.0x cheaper ($0.15 vs $0.60 per million) and work measured by SciCode or LMArena Text: coding, where it leads.
Which is cheaper, gpt-oss-20b or Solar Pro 4?
gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Solar Pro 4 costs $0.15 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, gpt-oss-20b or Solar Pro 4?
Solar Pro 4, with 524K tokens against 131K.
How many benchmarks is the gpt-oss-20b vs Solar Pro 4 comparison based on?
35 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Solar Pro 4's on 1. Where only one model has a result, the page says so instead of naming a winner.