Claude Sonnet 4.5 vs gpt-oss-120b
Claude Sonnet 4.5 leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 20.7 to 11.6, and gpt-oss-120b costs 30.0x less per output token ($0.50 vs $15.00 per million). Updated October 22, 2026; 61 benchmarks have a result for both.
Claude Sonnet 4.5 or gpt-oss-120b: which to pick
Only Claude Sonnet 4.5 has a coding score, 39.5 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding.
Pick gpt-oss-120b for output tokens 30.0x cheaper ($0.50 vs $15.00 per million) and a lower cost per solved task ($0.51 against $1.16).
- Shared results
- 61
- Claude Sonnet 4.5 only
- 34
- gpt-oss-120b only
- 20
- Like-for-like categories
- 8 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
Only Claude Sonnet 4.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 20.7 against 11.6.
Same board, both measured
Agentic work
AA Agentic Index
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 15.8 against 3.7.
Same board, both measured
Reasoning
GPQA Diamond
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 81.6% against 78.5%.
Same board, both measured
Math
AIME
gpt-oss-120b
gpt-oss-120b leads, 92.6% against 88.2%.
Same board, both measured
Knowledge
MMLU Pro
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 87.4% against 79.2%.
Same board, both measured
Web design
Design Arena: websites
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 1189 against 967.
Same board, both measured
Long documents
Listed context window
Claude Sonnet 4.5
Claude Sonnet 4.5 takes 1M tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-120b
Claude Sonnet 4.5 $0.011, gpt-oss-120b $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
gpt-oss-120b
Claude Sonnet 4.5 $1.16, gpt-oss-120b $0.51.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Sonnet 4.5 39.5 from 3 benchmarks, gpt-oss-120b not benchmarked.
- Widest category
- Web design, 27.0 points apart on average over 6 shared benchmarks.
- Widest single gap
- SWE-bench Verified: Claude Sonnet 4.5 74.8% against gpt-oss-120b 26.0%, 48.8 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.5 $15.00 against gpt-oss-120b $0.50 per million output tokens, 30.0x apart.
- Context window
- Claude Sonnet 4.5 takes 1M tokens, gpt-oss-120b 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 Sonnet 4.5 | Bars | gpt-oss-120b | Ties |
|---|---|---|---|---|
| Coding | 6 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 7 | 1 | ||
| Math | 3 | 2 | ||
| Knowledge | 10 | 0 | ||
| Web design | 6 | 0 | ||
| General | 19 | 0 | ||
| All shared boards | 56 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index62
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 41.8% | Only gpt-oss-120b measured |
| SWE-bench Verified | 74.8% | 26.0% | Claude Sonnet 4.5 |
| SWE-bench Multilingual | 67.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev | 1394 | Not measured | Only Claude Sonnet 4.5 measured |
| AA Coding Index | 52.1 | 30.4 | Claude Sonnet 4.5 |
| LiveCodeBench (Vals AI) | 73.0% | 83.2% | gpt-oss-120b |
| SWE-bench Verified (Vals AI) | 70.0% | 33.6% | Claude Sonnet 4.5 |
| Vibe Code Bench (Vals AI) | 22.6% | Not measured | Only Claude Sonnet 4.5 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 87.8% | Only gpt-oss-120b measured |
| SciCode | Not measured | 34.0% | Only gpt-oss-120b measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 23.5% | Only gpt-oss-120b measured |
| Terminal-Bench | 46.5% | 18.7% | Claude Sonnet 4.5 |
| GSO-Bench | 14.7% | Not measured | Only Claude Sonnet 4.5 measured |
| WeirdML | 47.7% | 48.2% | gpt-oss-120b |
| Cybench | 60.0% | Not measured | Only Claude Sonnet 4.5 measured |
| ALE-Bench | Not measured | 575.6 | Only gpt-oss-120b measured |
| LMArena Text: coding | 1488 | 1379 | Claude Sonnet 4.5 |
| LMArena Text: software and IT | 1473 | 1387 | Claude Sonnet 4.5 |
| LMArena WebDev: React | 1386 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev: HTML | 1399 | Not measured | Only Claude Sonnet 4.5 measured |
| SciCode | Not measured | 7.7% | Only gpt-oss-120b measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.7 | 11.6 | Claude Sonnet 4.5 |
| Epoch Capabilities Index | 146.7 | 139.8 | Claude Sonnet 4.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| AA Agentic Index | 15.8 | 3.7 | Claude Sonnet 4.5 |
| Design Arena: agents building web apps | 1060 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building full-stack apps | 1050 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building mobile apps | 1137 | Not measured | Only Claude Sonnet 4.5 measured |
| τ²-Bench Telecom | Not measured | 65.8% | Only gpt-oss-120b measured |
| APEX-Agents | Not measured | 4.4% | Only gpt-oss-120b measured |
| METR time horizons | 67.4% | 56.6% | Claude Sonnet 4.5 |
| Remote Labor Index | 2.1% | Not measured | Only Claude Sonnet 4.5 measured |
| GDPval | 42.5% | Not measured | Only Claude Sonnet 4.5 measured |
| DeepResearch Bench | 52.6% | Not measured | Only Claude Sonnet 4.5 measured |
| OSWorld | 62.9% | Not measured | Only Claude Sonnet 4.5 measured |
| Vending-Bench 2 | $3,839 | -$22 | Claude Sonnet 4.5 |
| Berkeley Function Calling Leaderboard (BFCL) | 73.2% | Not measured | Only Claude Sonnet 4.5 measured |
| BrowseComp-Plus | Not measured | 67.0% | Only gpt-oss-120b measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| GPQA Diamond | 81.6% | 78.5% | Claude Sonnet 4.5 |
| MMMU Pro (Vals AI) | 79.3% | Not measured | Only Claude Sonnet 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 78.2% | Only gpt-oss-120b measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 19.6% | Only gpt-oss-120b measured |
| GPQA Diamond (Epoch AI run) | 82.3% | 75.8% | Claude Sonnet 4.5 |
| ARC-AGI | 63.7% | Not measured | Only Claude Sonnet 4.5 measured |
| ARC-AGI-2 | 13.6% | Not measured | Only Claude Sonnet 4.5 measured |
| SimpleBench | 54.3% | 22.1% | Claude Sonnet 4.5 |
| Chess puzzles | 10.0% | Not measured | Only Claude Sonnet 4.5 measured |
| Mystery game puzzles | 17.0% | 2.0% | Claude Sonnet 4.5 |
| EBR-bench | 2.4% | Not measured | Only Claude Sonnet 4.5 measured |
| VPCT | 39.8% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: hard prompts | 1462 | 1364 | Claude Sonnet 4.5 |
| LMArena Text: expert | 1483 | 1356 | Claude Sonnet 4.5 |
| LMArena Text: hard prompts in English | 1471 | 1368 | Claude Sonnet 4.5 |
| Kagi LLM Benchmark | 57.9% | 58.6% | gpt-oss-120b |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| AIME | 88.2% | 92.6% | gpt-oss-120b |
| MATH 500 (Vals AI) | Not measured | 94.8% | Only gpt-oss-120b measured |
| MGSM (Vals AI) | 94.3% | 92.0% | Claude Sonnet 4.5 |
| AA Math Index | Not measured | 93.4 | Only gpt-oss-120b measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 93.4% | Only gpt-oss-120b measured |
| OTIS Mock AIME | 77.8% | 88.9% | gpt-oss-120b |
| FrontierMath, tiers 1 to 3 | 23.9% | Not measured | Only Claude Sonnet 4.5 measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only Claude Sonnet 4.5 measured |
| ProofBench | 19.0% | Not measured | Only Claude Sonnet 4.5 measured |
| MATH level 5 | 97.7% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: math | 1449 | 1389 | Claude Sonnet 4.5 |
| LMArena Text: mathematical work | 1462 | 1386 | Claude Sonnet 4.5 |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| MMLU Pro | 87.4% | 79.2% | Claude Sonnet 4.5 |
| LegalBench (Vals AI) | 84.1% | 75.9% | Claude Sonnet 4.5 |
| CaseLaw (Vals AI) | 62.2% | 48.8% | Claude Sonnet 4.5 |
| CorpFin (Vals AI) | 62.0% | 58.2% | Claude Sonnet 4.5 |
| TaxEval (Vals AI) | 73.3% | 71.6% | Claude Sonnet 4.5 |
| MortgageTax (Vals AI) | 64.0% | Not measured | Only Claude Sonnet 4.5 measured |
| MedQA (Vals AI) | 94.7% | 91.4% | Claude Sonnet 4.5 |
| MedCode (Vals AI) | 44.1% | Not measured | Only Claude Sonnet 4.5 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 80.8% | Only gpt-oss-120b measured |
| SimpleQA Verified | 30.7% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: science | 1448 | 1382 | Claude Sonnet 4.5 |
| LMArena Text: medicine and healthcare | 1444 | 1388 | Claude Sonnet 4.5 |
| LMArena Text: legal and government | 1451 | 1355 | Claude Sonnet 4.5 |
| LMArena Text: business and finance | 1440 | 1359 | Claude Sonnet 4.5 |
| FACTS Benchmark Suite | 40.6% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| Design Arena: websites | 1189 | 967 | Claude Sonnet 4.5 |
| Design Arena: UI components | 1170 | 924 | Claude Sonnet 4.5 |
| Design Arena: game dev | 1166 | 992 | Claude Sonnet 4.5 |
| Design Arena: data viz | 1167 | 987 | Claude Sonnet 4.5 |
| Design Arena: 3D | 1157 | 901 | Claude Sonnet 4.5 |
| Design Arena: all code categories | 1182 | 962 | Claude Sonnet 4.5 |
| Design Arena: SVG | 1115 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: ASCII art | 1205 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 36.1% | Not measured | Only Claude Sonnet 4.5 measured |
| MedScribe (Vals AI) | 84.5% | Not measured | Only Claude Sonnet 4.5 measured |
| IFBench | Not measured | 69.0% | Only gpt-oss-120b measured |
| Long context reasoning (AA-LCR) | Not measured | 52.0% | Only gpt-oss-120b measured |
| DTBench | 83.2% | 76.3% | Claude Sonnet 4.5 |
| LMCA | 38.8% | 22.1% | Claude Sonnet 4.5 |
| Fiction.LiveBench | Not measured | 44.4% | Only gpt-oss-120b measured |
| Creative writing (Lech Mazur) | Not measured | 77.1% | Only gpt-oss-120b measured |
| Surface Evolver Bench | Not measured | 25.0% | Only gpt-oss-120b measured |
| LMArena Text | 1438 | 1366 | Claude Sonnet 4.5 |
| LMArena Text: instruction following | 1459 | 1318 | Claude Sonnet 4.5 |
| LMArena Text: creative writing | 1442 | 1274 | Claude Sonnet 4.5 |
| LMArena Text: English | 1450 | 1375 | Claude Sonnet 4.5 |
| LMArena Text: non-English | 1425 | 1351 | Claude Sonnet 4.5 |
| LMArena Text: Chinese | 1460 | 1385 | Claude Sonnet 4.5 |
| LMArena Text: German | 1427 | 1353 | Claude Sonnet 4.5 |
| LMArena Text: Japanese | 1390 | 1331 | Claude Sonnet 4.5 |
| LMArena Text: Korean | 1402 | 1282 | Claude Sonnet 4.5 |
| LMArena Text: French | 1459 | 1370 | Claude Sonnet 4.5 |
| LMArena Text: Spanish | 1458 | 1389 | Claude Sonnet 4.5 |
| LMArena Text: Russian | 1437 | 1343 | Claude Sonnet 4.5 |
| LMArena Text: Polish | 1423 | 1353 | Claude Sonnet 4.5 |
| LMArena Text: multi-turn | 1465 | 1340 | Claude Sonnet 4.5 |
| LMArena Text: longer queries | 1475 | 1319 | Claude Sonnet 4.5 |
| LMArena Text: writing and language | 1442 | 1306 | Claude Sonnet 4.5 |
| LMArena Text: entertainment and media | 1428 | 1292 | Claude Sonnet 4.5 |
| LMArena Document | 1450 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 19 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.5 | gpt-oss-120b | 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-120b costs less
Repository review
50K input + 3K output tokens
gpt-oss-120b costs less
Agent loop
200K input + 10K output tokens
gpt-oss-120b 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 Sonnet 4.5 | OpenAI gpt-oss-120b |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | Open weights |
| Released | September 29, 2025 | August 5, 2025 |
| Context window | 1M | 131K |
| Input $/Mtok | $3.00 | $0.10 |
| Output $/Mtok | $15.00 | $0.50 |
| Coding index | 39.5 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $1.16 | $0.51 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.5 better than gpt-oss-120b for coding?
Only Claude Sonnet 4.5 has a coding score, 39.5 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 30.0x cheaper ($0.50 vs $15.00 per million) and a lower cost per solved task ($0.51 against $1.16).
Which is cheaper, Claude Sonnet 4.5 or gpt-oss-120b?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; gpt-oss-120b costs $0.10 and $0.50. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and gpt-oss-120b $0.51.
Which has the bigger context window, Claude Sonnet 4.5 or gpt-oss-120b?
Claude Sonnet 4.5, with 1M tokens against 131K.
How many benchmarks is the Claude Sonnet 4.5 vs gpt-oss-120b comparison based on?
61 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.5's coding index rests on 3 independent benchmarks and gpt-oss-120b's on 1. Where only one model has a result, the page says so instead of naming a winner.