Claude Opus 4.1 vs gpt-oss-20b
Claude Opus 4.1 leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 22.8 to 10.0, and gpt-oss-20b costs 500.0x less per output token ($0.15 vs $75.00 per million). Updated October 21, 2026; 46 benchmarks have a result for both.
Claude Opus 4.1 or gpt-oss-20b: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Claude Opus 4.1 for a larger context window (200K against 131K tokens) and work measured by LiveCodeBench (Vals AI) or AIME, where it leads.
- Shared results
- 46
- Claude Opus 4.1 only
- 27
- gpt-oss-20b only
- 16
- 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
Claude Opus 4.1
Claude Opus 4.1 leads, 22.8 against 10.0.
Same board, both measured
Reasoning
GPQA Diamond
Claude Opus 4.1
Claude Opus 4.1 leads, 76.3% against 68.9%.
Same board, both measured
Math
AIME
gpt-oss-20b
gpt-oss-20b leads, 86.0% against 78.2%.
Same board, both measured
Knowledge
MMLU Pro
Claude Opus 4.1
Claude Opus 4.1 leads, 87.9% against 71.6%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 4.1
Claude Opus 4.1 leads, 1177 against 852.
Same board, both measured
Long documents
Listed context window
Claude Opus 4.1
Claude Opus 4.1 takes 200K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-20b
Claude Opus 4.1 $0.052, gpt-oss-20b $0.0001 per turn.
List prices
At a glance
- Coding index
- Claude Opus 4.1 not benchmarked, gpt-oss-20b not benchmarked.
- Widest category
- Web design, 34.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- Design Arena: websites: Claude Opus 4.1 1177 against gpt-oss-20b 852, 40.6 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.1 $75.00 against gpt-oss-20b $0.15 per million output tokens, 500.0x apart.
- Context window
- Claude Opus 4.1 takes 200K tokens, gpt-oss-20b 131K.
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 | Claude Opus 4.1 | Bars | gpt-oss-20b | Ties |
|---|---|---|---|---|
| Coding | 4 | 1 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 5 | 1 | ||
| Knowledge | 8 | 0 | ||
| Web design | 2 | 0 | ||
| General | 18 | 0 | ||
| All shared boards | 44 | 2 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index41
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| LMArena WebDev | 1390 | Not measured | Only Claude Opus 4.1 measured |
| LiveCodeBench (Vals AI) | 66.5% | 80.4% | gpt-oss-20b |
| LiveCodeBench (Artificial Analysis run) | Not measured | 77.7% | Only gpt-oss-20b measured |
| SciCode | Not measured | 38.9% | Only gpt-oss-20b measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 10.6% | Only gpt-oss-20b measured |
| Terminal-Bench | 38.0% | 3.4% | Claude Opus 4.1 |
| WeirdML | 45.9% | 40.9% | Claude Opus 4.1 |
| Cybench | 42.0% | Not measured | Only Claude Opus 4.1 measured |
| ALE-Bench | Not measured | 566.0 | Only gpt-oss-20b measured |
| LMArena Text: coding | 1479 | 1307 | Claude Opus 4.1 |
| LMArena Text: software and IT | 1456 | 1311 | Claude Opus 4.1 |
| LMArena WebDev: HTML | 1399 | Not measured | Only Claude Opus 4.1 measured |
| SciCode | 4.6% | Not measured | Only Claude Opus 4.1 measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 10.0 | Claude Opus 4.1 |
| Epoch Capabilities Index | 144.1 | 137.7 | Claude Opus 4.1 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 60.2% | Only gpt-oss-20b measured |
| METR time horizons | 66.8% | Not measured | Only Claude Opus 4.1 measured |
| GDPval | 43.6% | Not measured | Only Claude Opus 4.1 measured |
| DeepResearch Bench | 48.3% | Not measured | Only Claude Opus 4.1 measured |
| BrowseComp-Plus | Not measured | 50.6% | Only gpt-oss-20b measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| GPQA Diamond | 76.3% | 68.9% | Claude Opus 4.1 |
| MMMU Pro (Vals AI) | 77.5% | Not measured | Only Claude Opus 4.1 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 68.8% | Only gpt-oss-20b measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 11.0% | Only gpt-oss-20b measured |
| GPQA Diamond (Epoch AI run) | 77.3% | 60.8% | Claude Opus 4.1 |
| SimpleBench | 60.0% | Not measured | Only Claude Opus 4.1 measured |
| Mystery game puzzles | 21.0% | Not measured | Only Claude Opus 4.1 measured |
| EBR-bench | 7.9% | Not measured | Only Claude Opus 4.1 measured |
| VPCT | 35.0% | Not measured | Only Claude Opus 4.1 measured |
| LMArena Text: hard prompts | 1442 | 1274 | Claude Opus 4.1 |
| LMArena Text: expert | 1438 | 1258 | Claude Opus 4.1 |
| LMArena Text: hard prompts in English | 1451 | 1292 | Claude Opus 4.1 |
| Kagi LLM Benchmark | Not measured | 53.2% | Only gpt-oss-20b measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| AIME | 78.2% | 86.0% | gpt-oss-20b |
| MATH 500 (Vals AI) | 95.4% | 94.2% | Claude Opus 4.1 |
| MGSM (Vals AI) | 94.4% | 89.0% | Claude Opus 4.1 |
| AA Math Index | Not measured | 89.3 | Only gpt-oss-20b measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 89.3% | Only gpt-oss-20b measured |
| OTIS Mock AIME | 68.9% | 65.3% | Claude Opus 4.1 |
| FrontierMath, tiers 1 to 3 | 12.6% | Not measured | Only Claude Opus 4.1 measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only Claude Opus 4.1 measured |
| LMArena Text: math | 1431 | 1317 | Claude Opus 4.1 |
| LMArena Text: mathematical work | 1434 | 1305 | Claude Opus 4.1 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| MMLU Pro | 87.9% | 71.6% | Claude Opus 4.1 |
| LegalBench (Vals AI) | 83.5% | 70.8% | Claude Opus 4.1 |
| CaseLaw (Vals AI) | Not measured | 43.8% | Only gpt-oss-20b measured |
| CorpFin (Vals AI) | Not measured | 53.1% | Only gpt-oss-20b measured |
| TaxEval (Vals AI) | 73.7% | 63.7% | Claude Opus 4.1 |
| MortgageTax (Vals AI) | 61.1% | Not measured | Only Claude Opus 4.1 measured |
| MedQA (Vals AI) | 93.6% | 82.9% | Claude Opus 4.1 |
| MedCode (Vals AI) | 47.2% | Not measured | Only Claude Opus 4.1 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 74.8% | Only gpt-oss-20b measured |
| LMArena Text: science | 1422 | 1296 | Claude Opus 4.1 |
| LMArena Text: medicine and healthcare | 1416 | 1310 | Claude Opus 4.1 |
| LMArena Text: legal and government | 1421 | 1280 | Claude Opus 4.1 |
| LMArena Text: business and finance | 1406 | 1284 | Claude Opus 4.1 |
| FACTS Benchmark Suite | 40.4% | Not measured | Only Claude Opus 4.1 measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| Design Arena: websites | 1177 | 852 | Claude Opus 4.1 |
| Design Arena: UI components | 1165 | Not measured | Only Claude Opus 4.1 measured |
| Design Arena: game dev | 1171 | Not measured | Only Claude Opus 4.1 measured |
| Design Arena: data viz | 1166 | 933 | Claude Opus 4.1 |
| Design Arena: 3D | 1153 | Not measured | Only Claude Opus 4.1 measured |
| Design Arena: all code categories | 1171 | Not measured | Only Claude Opus 4.1 measured |
| Design Arena: SVG | 1152 | Not measured | Only Claude Opus 4.1 measured |
| Design Arena: ASCII art | 1167 | Not measured | Only Claude Opus 4.1 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 31.4% | Not measured | Only Claude Opus 4.1 measured |
| MedScribe (Vals AI) | 73.9% | Not measured | Only Claude Opus 4.1 measured |
| IFBench | Not measured | 65.1% | Only gpt-oss-20b measured |
| Long context reasoning (AA-LCR) | Not measured | 34.7% | Only gpt-oss-20b measured |
| DTBench | 80.0% | 68.0% | Claude Opus 4.1 |
| LMCA | 37.1% | 14.5% | Claude Opus 4.1 |
| Creative writing (Lech Mazur) | 84.7% | Not measured | Only Claude Opus 4.1 measured |
| LMArena Text | 1419 | 1288 | Claude Opus 4.1 |
| LMArena Text: instruction following | 1435 | 1236 | Claude Opus 4.1 |
| LMArena Text: creative writing | 1412 | 1201 | Claude Opus 4.1 |
| LMArena Text: English | 1433 | 1303 | Claude Opus 4.1 |
| LMArena Text: non-English | 1405 | 1269 | Claude Opus 4.1 |
| LMArena Text: Chinese | 1427 | 1315 | Claude Opus 4.1 |
| LMArena Text: German | 1413 | 1255 | Claude Opus 4.1 |
| LMArena Text: Japanese | 1377 | 1244 | Claude Opus 4.1 |
| LMArena Text: Korean | 1381 | 1236 | Claude Opus 4.1 |
| LMArena Text: French | 1433 | Not measured | Only Claude Opus 4.1 measured |
| LMArena Text: Spanish | 1448 | 1267 | Claude Opus 4.1 |
| LMArena Text: Russian | 1422 | 1278 | Claude Opus 4.1 |
| LMArena Text: Polish | 1413 | 1252 | Claude Opus 4.1 |
| LMArena Text: multi-turn | 1444 | 1268 | Claude Opus 4.1 |
| LMArena Text: longer queries | 1455 | 1250 | Claude Opus 4.1 |
| LMArena Text: writing and language | 1418 | 1238 | Claude Opus 4.1 |
| LMArena Text: entertainment and media | 1398 | 1216 | Claude Opus 4.1 |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.1 | gpt-oss-20b | 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 | Anthropic Claude Opus 4.1 | OpenAI gpt-oss-20b |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | Open weights |
| Released | August 5, 2025 | August 5, 2025 |
| Context window | 200K | 131K |
| Input $/Mtok | $15.00 | $0.03 |
| Output $/Mtok | $75.00 | $0.15 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.1 better than gpt-oss-20b for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Claude Opus 4.1 for a larger context window (200K against 131K tokens) and work measured by LiveCodeBench (Vals AI) or AIME, where it leads.
Which is cheaper, Claude Opus 4.1 or gpt-oss-20b?
Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Opus 4.1 or gpt-oss-20b?
Claude Opus 4.1, with 200K tokens against 131K.
How many benchmarks is the Claude Opus 4.1 vs gpt-oss-20b comparison based on?
46 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.1's coding index rests on 1 independent benchmark and gpt-oss-20b's on 0. Where only one model has a result, the page says so instead of naming a winner.