gpt-oss-120b vs o1
o1 leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 15.2 to 11.6, and gpt-oss-120b costs 120.0x less per output token ($0.50 vs $60.00 per million). Updated October 22, 2026; 58 benchmarks have a result for both.
gpt-oss-120b or o1: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick gpt-oss-120b for output tokens 120.0x cheaper ($0.50 vs $60.00 per million) and work measured by Aider polyglot or AA Coding Index, where it leads.
- Shared results
- 58
- gpt-oss-120b only
- 23
- o1 only
- 11
- 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
o1
o1 leads, 15.2 against 11.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only gpt-oss-120b has a AA Agentic Index result, 3.7.
Directional only
Reasoning
GPQA Diamond
gpt-oss-120b
gpt-oss-120b leads, 78.5% against 73.2%.
Same board, both measured
Math
AIME
gpt-oss-120b
gpt-oss-120b leads, 92.6% against 71.5%.
Same board, both measured
Knowledge
MMLU Pro
o1
o1 leads, 83.5% against 79.2%.
Same board, both measured
Web design
Design Arena: websites
No call
Only gpt-oss-120b has a Design Arena: websites result, 967.
Directional only
Long documents
Listed context window
o1
o1 takes 200K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-120b
gpt-oss-120b $0.0003, o1 $0.045 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only gpt-oss-120b has the number, $0.51.
Directional only
At a glance
- Coding index
- gpt-oss-120b not benchmarked, o1 not benchmarked.
- Widest category
- Coding, 11.5 points apart on average over 9 shared benchmarks.
- Widest single gap
- Fiction.LiveBench: gpt-oss-120b 44.4% against o1 83.3%, 38.9 points apart on a 0 to 100 scale.
- Output price
- gpt-oss-120b $0.50 against o1 $60.00 per million output tokens, 120.0x apart.
- Context window
- gpt-oss-120b takes 131K tokens, o1 200K.
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-120b | Bars | o1 | Ties |
|---|---|---|---|---|
| Coding | 7 | 2 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 3 | 5 | ||
| Math | 5 | 1 | ||
| Knowledge | 3 | 6 | ||
| General | 6 | 16 | ||
| All shared boards | 26 | 32 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index72
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| Aider polyglot | 41.8% | 61.7% | o1 |
| SWE-bench Verified | 26.0% | Not measured | Only gpt-oss-120b measured |
| AA Coding Index | 30.4 | 39.7 | o1 |
| LiveCodeBench (Vals AI) | 83.2% | 50.3% | gpt-oss-120b |
| SWE-bench Verified (Vals AI) | 33.6% | Not measured | Only gpt-oss-120b measured |
| LiveCodeBench (Artificial Analysis run) | 87.8% | 67.9% | gpt-oss-120b |
| SciCode | 34.0% | Not measured | Only gpt-oss-120b measured |
| Terminal-Bench Hard (Artificial Analysis run) | 23.5% | 12.9% | gpt-oss-120b |
| Terminal-Bench | 18.7% | Not measured | Only gpt-oss-120b measured |
| WeirdML | 48.2% | 46.1% | gpt-oss-120b |
| ALE-Bench | 575.6 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: coding | 1379 | 1367 | gpt-oss-120b |
| LMArena Text: software and IT | 1387 | 1366 | gpt-oss-120b |
| SciCode | 7.7% | 4.6% | gpt-oss-120b |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.6 | 15.2 | o1 |
| Epoch Capabilities Index | 139.8 | 141.7 | o1 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| AA Agentic Index | 3.7 | Not measured | Only gpt-oss-120b measured |
| τ²-Bench Telecom | 65.8% | 62.6% | gpt-oss-120b |
| APEX-Agents | 4.4% | Not measured | Only gpt-oss-120b measured |
| METR time horizons | 56.6% | 51.1% | gpt-oss-120b |
| Vending-Bench 2 | -$22 | Not measured | Only gpt-oss-120b measured |
| BrowseComp-Plus | 67.0% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index35
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | 73.2% | gpt-oss-120b |
| MMMU Pro (Vals AI) | Not measured | 77.4% | Only o1 measured |
| GPQA Diamond (Artificial Analysis run) | 78.2% | 74.7% | gpt-oss-120b |
| Humanity's Last Exam (Artificial Analysis run) | 19.6% | 7.0% | gpt-oss-120b |
| GPQA Diamond (Epoch AI run) | 75.8% | 76.8% | o1 |
| ARC-AGI | Not measured | 30.7% | Only o1 measured |
| SimpleBench | 22.1% | 40.1% | o1 |
| Chess puzzles | Not measured | 10.0% | Only o1 measured |
| Mystery game puzzles | 2.0% | Not measured | Only gpt-oss-120b measured |
| VPCT | Not measured | 37.0% | Only o1 measured |
| LMArena Text: hard prompts | 1364 | 1371 | o1 |
| LMArena Text: expert | 1356 | 1361 | o1 |
| LMArena Text: hard prompts in English | 1368 | 1372 | o1 |
| Kagi LLM Benchmark | 58.6% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| AIME | 92.6% | 71.5% | gpt-oss-120b |
| MATH 500 (Vals AI) | 94.8% | 90.4% | gpt-oss-120b |
| MGSM (Vals AI) | 92.0% | 89.3% | gpt-oss-120b |
| AA Math Index | 93.4 | Not measured | Only gpt-oss-120b measured |
| AIME 2025 (Artificial Analysis run) | 93.4% | Not measured | Only gpt-oss-120b measured |
| OTIS Mock AIME | 88.9% | 73.3% | gpt-oss-120b |
| FrontierMath, tiers 1 to 3 | Not measured | 14.7% | Only o1 measured |
| MATH level 5 | Not measured | 94.7% | Only o1 measured |
| LMArena Text: math | 1389 | 1388 | gpt-oss-120b |
| LMArena Text: mathematical work | 1386 | 1390 | o1 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index36
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| MMLU Pro | 79.2% | 83.5% | o1 |
| LegalBench (Vals AI) | 75.9% | 80.4% | o1 |
| CaseLaw (Vals AI) | 48.8% | Not measured | Only gpt-oss-120b measured |
| CorpFin (Vals AI) | 58.2% | Not measured | Only gpt-oss-120b measured |
| TaxEval (Vals AI) | 71.6% | 74.3% | o1 |
| MedQA (Vals AI) | 91.4% | 96.5% | o1 |
| MMLU Pro (Artificial Analysis run) | 80.8% | 84.1% | o1 |
| SimpleQA Verified | Not measured | 41.1% | Only o1 measured |
| GeoBench | Not measured | 80.0% | Only o1 measured |
| LMArena Text: science | 1382 | 1369 | gpt-oss-120b |
| LMArena Text: medicine and healthcare | 1388 | 1355 | gpt-oss-120b |
| LMArena Text: legal and government | 1355 | 1368 | o1 |
| LMArena Text: business and finance | 1359 | 1328 | gpt-oss-120b |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| Design Arena: websites | 967 | Not measured | Only gpt-oss-120b measured |
| Design Arena: UI components | 924 | Not measured | Only gpt-oss-120b measured |
| Design Arena: game dev | 992 | Not measured | Only gpt-oss-120b measured |
| Design Arena: data viz | 987 | Not measured | Only gpt-oss-120b measured |
| Design Arena: 3D | 901 | Not measured | Only gpt-oss-120b measured |
| Design Arena: all code categories | 962 | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index616
| Benchmark | gpt-oss-120b | o1 | Leader |
|---|---|---|---|
| IFBench | 69.0% | 70.3% | o1 |
| Long context reasoning (AA-LCR) | 52.0% | 65.0% | o1 |
| DTBench | 76.3% | 74.7% | gpt-oss-120b |
| LMCA | 22.1% | 22.3% | o1 |
| Fiction.LiveBench | 44.4% | 83.3% | o1 |
| Creative writing (Lech Mazur) | 77.1% | 70.2% | gpt-oss-120b |
| Surface Evolver Bench | 25.0% | Not measured | Only gpt-oss-120b measured |
| LMArena Text | 1366 | 1366 | o1 |
| LMArena Text: instruction following | 1318 | 1367 | o1 |
| LMArena Text: creative writing | 1274 | 1347 | o1 |
| LMArena Vision | Not measured | 1168 | Only o1 measured |
| LMArena Text: English | 1375 | 1372 | gpt-oss-120b |
| LMArena Text: non-English | 1351 | 1358 | o1 |
| LMArena Text: Chinese | 1385 | 1394 | o1 |
| LMArena Text: German | 1353 | 1337 | gpt-oss-120b |
| LMArena Text: Japanese | 1331 | 1346 | o1 |
| LMArena Text: Korean | 1282 | 1396 | o1 |
| LMArena Text: French | 1370 | 1344 | gpt-oss-120b |
| LMArena Text: Spanish | 1389 | 1345 | gpt-oss-120b |
| LMArena Text: Russian | 1343 | 1356 | o1 |
| LMArena Text: Polish | 1353 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: multi-turn | 1340 | 1355 | o1 |
| LMArena Text: longer queries | 1319 | 1378 | o1 |
| LMArena Text: writing and language | 1306 | 1360 | o1 |
| LMArena Text: entertainment and media | 1292 | 1358 | o1 |
| LMArena Vision: English | Not measured | 1162 | Only o1 measured |
| LMArena Vision: Chinese | Not measured | 1235 | Only o1 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 | gpt-oss-120b | o1 | 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 | OpenAI gpt-oss-120b | OpenAI o1 |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | August 5, 2025 | December 17, 2024 |
| Context window | 131K | 200K |
| Input $/Mtok | $0.10 | $15.00 |
| Output $/Mtok | $0.50 | $60.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | $0.51 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is gpt-oss-120b better than o1 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 120.0x cheaper ($0.50 vs $60.00 per million) and work measured by Aider polyglot or AA Coding Index, where it leads.
Which is cheaper, gpt-oss-120b or o1?
gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; o1 costs $15.00 and $60.00. Cost per solved task is known for gpt-oss-120b only.
Which has the bigger context window, gpt-oss-120b or o1?
o1, with 200K tokens against 131K.
How many benchmarks is the gpt-oss-120b vs o1 comparison based on?
58 benchmarks have a result for both models as of October 22, 2026. gpt-oss-120b's coding index rests on 1 independent benchmark and o1's on 0. Where only one model has a result, the page says so instead of naming a winner.