GPT-5.3-Codex vs gpt-oss-120b
GPT-5.3-Codex leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 32.5 to 11.6, and gpt-oss-120b costs 28.0x less per output token ($0.50 vs $14.00 per million). Updated October 22, 2026; 21 benchmarks have a result for both.
GPT-5.3-Codex or gpt-oss-120b: which to pick
Only GPT-5.3-Codex has a coding score, 60.0 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 28.0x cheaper ($0.50 vs $14.00 per million) and a lower cost per solved task ($0.51 against $0.59).
- Shared results
- 21
- GPT-5.3-Codex only
- 13
- gpt-oss-120b only
- 60
- Like-for-like categories
- 6 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 GPT-5.3-Codex has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.3-Codex
GPT-5.3-Codex leads, 32.5 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
No call
Only gpt-oss-120b has a GPQA Diamond result, 78.5%.
Directional only
Math
AIME
No call
Only gpt-oss-120b has a AIME result, 92.6%.
Directional only
Knowledge
MMLU Pro
No call
Only gpt-oss-120b has a MMLU Pro result, 79.2%.
Directional only
Web design
Design Arena: websites
GPT-5.3-Codex
GPT-5.3-Codex leads, 1162 against 967.
Same board, both measured
Long documents
Listed context window
GPT-5.3-Codex
GPT-5.3-Codex takes 400K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-120b
GPT-5.3-Codex $0.0088, gpt-oss-120b $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
gpt-oss-120b
GPT-5.3-Codex $0.59, gpt-oss-120b $0.51.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.3-Codex 60.0 from 3 benchmarks, gpt-oss-120b not benchmarked.
- Widest category
- Coding, 34.1 points apart on average over 6 shared benchmarks.
- Widest single gap
- Terminal-Bench: GPT-5.3-Codex 78.4% against gpt-oss-120b 18.7%, 59.7 points apart on a 0 to 100 scale.
- Output price
- GPT-5.3-Codex $14.00 against gpt-oss-120b $0.50 per million output tokens, 28.0x apart.
- Context window
- GPT-5.3-Codex takes 400K 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 | GPT-5.3-Codex | Bars | gpt-oss-120b | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 2 | 0 | ||
| Web design | 6 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 21 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 41.8% | Only gpt-oss-120b measured |
| SWE-bench Verified | Not measured | 26.0% | Only gpt-oss-120b measured |
| LMArena WebDev | 1407 | Not measured | Only GPT-5.3-Codex measured |
| AA Coding Index | Not measured | 30.4 | Only gpt-oss-120b measured |
| LiveCodeBench (Vals AI) | 87.3% | 83.2% | GPT-5.3-Codex |
| SWE-bench Verified (Vals AI) | 78.0% | 33.6% | GPT-5.3-Codex |
| Vibe Code Bench (Vals AI) | 61.8% | Not measured | Only GPT-5.3-Codex measured |
| IOI (Vals AI) | 53.8% | Not measured | Only GPT-5.3-Codex 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) | 53.0% | 23.5% | GPT-5.3-Codex |
| Terminal-Bench | 78.4% | 18.7% | GPT-5.3-Codex |
| WeirdML | 79.3% | 48.2% | GPT-5.3-Codex |
| ALE-Bench | 1655.2 | 575.6 | GPT-5.3-Codex |
| LMArena Text: coding | Not measured | 1379 | Only gpt-oss-120b measured |
| LMArena Text: software and IT | Not measured | 1387 | Only gpt-oss-120b measured |
| LMArena WebDev: React | 1395 | Not measured | Only GPT-5.3-Codex measured |
| LMArena WebDev: HTML | 1422 | Not measured | Only GPT-5.3-Codex measured |
| LMArena WebDev: from an image | 1443 | Not measured | Only GPT-5.3-Codex measured |
| SciCode | Not measured | 7.7% | Only gpt-oss-120b measured |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| AA Intelligence Index | 32.5 | 11.6 | GPT-5.3-Codex |
| Epoch Capabilities Index | 157.1 | 139.8 | GPT-5.3-Codex |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 3.7 | Only gpt-oss-120b measured |
| Design Arena: agents building web apps | 1032 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building full-stack apps | 983 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building mobile apps | 1053 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building Android apps | 1084 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building Godot games | 1124 | Not measured | Only GPT-5.3-Codex measured |
| τ²-Bench Telecom | 86.0% | 65.8% | GPT-5.3-Codex |
| APEX-Agents | Not measured | 4.4% | Only gpt-oss-120b measured |
| METR time horizons | 74.5% | 56.6% | GPT-5.3-Codex |
| Vending-Bench 2 | $5,940 | -$22 | GPT-5.3-Codex |
| BrowseComp-Plus | Not measured | 67.0% | Only gpt-oss-120b measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 78.5% | Only gpt-oss-120b measured |
| GPQA Diamond (Artificial Analysis run) | 91.5% | 78.2% | GPT-5.3-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 42.5% | 19.6% | GPT-5.3-Codex |
| GPQA Diamond (Epoch AI run) | Not measured | 75.8% | Only gpt-oss-120b measured |
| SimpleBench | Not measured | 22.1% | Only gpt-oss-120b measured |
| Mystery game puzzles | Not measured | 2.0% | Only gpt-oss-120b measured |
| LMArena Text: hard prompts | Not measured | 1364 | Only gpt-oss-120b measured |
| LMArena Text: expert | Not measured | 1356 | Only gpt-oss-120b measured |
| LMArena Text: hard prompts in English | Not measured | 1368 | Only gpt-oss-120b measured |
| Kagi LLM Benchmark | Not measured | 58.6% | Only gpt-oss-120b measured |
| Neither model has a result on the other 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| AIME | Not measured | 92.6% | Only gpt-oss-120b measured |
| MATH 500 (Vals AI) | Not measured | 94.8% | Only gpt-oss-120b measured |
| MGSM (Vals AI) | Not measured | 92.0% | Only gpt-oss-120b measured |
| 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 | Not measured | 88.9% | Only gpt-oss-120b measured |
| LMArena Text: math | Not measured | 1389 | Only gpt-oss-120b measured |
| LMArena Text: mathematical work | Not measured | 1386 | Only gpt-oss-120b measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 79.2% | Only gpt-oss-120b measured |
| LegalBench (Vals AI) | Not measured | 75.9% | Only gpt-oss-120b measured |
| CaseLaw (Vals AI) | Not measured | 48.8% | Only gpt-oss-120b measured |
| CorpFin (Vals AI) | Not measured | 58.2% | Only gpt-oss-120b measured |
| TaxEval (Vals AI) | Not measured | 71.6% | Only gpt-oss-120b measured |
| MedQA (Vals AI) | Not measured | 91.4% | Only gpt-oss-120b measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 80.8% | Only gpt-oss-120b measured |
| LMArena Text: science | Not measured | 1382 | Only gpt-oss-120b measured |
| LMArena Text: medicine and healthcare | Not measured | 1388 | Only gpt-oss-120b measured |
| LMArena Text: legal and government | Not measured | 1355 | Only gpt-oss-120b measured |
| LMArena Text: business and finance | Not measured | 1359 | Only gpt-oss-120b measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| Design Arena: websites | 1162 | 967 | GPT-5.3-Codex |
| Design Arena: UI components | 1134 | 924 | GPT-5.3-Codex |
| Design Arena: game dev | 1161 | 992 | GPT-5.3-Codex |
| Design Arena: data viz | 1164 | 987 | GPT-5.3-Codex |
| Design Arena: 3D | 1007 | 901 | GPT-5.3-Codex |
| Design Arena: all code categories | 1144 | 962 | GPT-5.3-Codex |
| Design Arena: SVG | 1129 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: ASCII art | 1152 | Not measured | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.3-Codex | gpt-oss-120b | Leader |
|---|---|---|---|
| IFBench | 75.4% | 69.0% | GPT-5.3-Codex |
| Long context reasoning (AA-LCR) | 83.3% | 52.0% | GPT-5.3-Codex |
| DTBench | Not measured | 76.3% | Only gpt-oss-120b measured |
| LMCA | Not measured | 22.1% | Only gpt-oss-120b measured |
| 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 | Not measured | 1366 | Only gpt-oss-120b measured |
| LMArena Text: instruction following | Not measured | 1318 | Only gpt-oss-120b measured |
| LMArena Text: creative writing | Not measured | 1274 | Only gpt-oss-120b measured |
| LMArena Text: English | Not measured | 1375 | Only gpt-oss-120b measured |
| LMArena Text: non-English | Not measured | 1351 | Only gpt-oss-120b measured |
| LMArena Text: Chinese | Not measured | 1385 | Only gpt-oss-120b measured |
| LMArena Text: German | Not measured | 1353 | Only gpt-oss-120b measured |
| LMArena Text: Japanese | Not measured | 1331 | Only gpt-oss-120b measured |
| LMArena Text: Korean | Not measured | 1282 | Only gpt-oss-120b measured |
| LMArena Text: French | Not measured | 1370 | Only gpt-oss-120b measured |
| LMArena Text: Spanish | Not measured | 1389 | Only gpt-oss-120b measured |
| LMArena Text: Russian | Not measured | 1343 | Only gpt-oss-120b measured |
| LMArena Text: Polish | Not measured | 1353 | Only gpt-oss-120b measured |
| LMArena Text: multi-turn | Not measured | 1340 | Only gpt-oss-120b measured |
| LMArena Text: longer queries | Not measured | 1319 | Only gpt-oss-120b measured |
| LMArena Text: writing and language | Not measured | 1306 | Only gpt-oss-120b measured |
| LMArena Text: entertainment and media | Not measured | 1292 | Only gpt-oss-120b measured |
| 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 | GPT-5.3-Codex | 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 | OpenAI GPT-5.3-Codex | OpenAI gpt-oss-120b |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | Open weights |
| Released | February 24, 2026 | August 5, 2025 |
| Context window | 400K | 131K |
| Input $/Mtok | $1.75 | $0.10 |
| Output $/Mtok | $14.00 | $0.50 |
| Coding index | 60.0 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $0.59 | $0.51 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.3-Codex better than gpt-oss-120b for coding?
Only GPT-5.3-Codex has a coding score, 60.0 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 28.0x cheaper ($0.50 vs $14.00 per million) and a lower cost per solved task ($0.51 against $0.59).
Which is cheaper, GPT-5.3-Codex or gpt-oss-120b?
GPT-5.3-Codex costs $1.75 per million input tokens and $14.00 per million output tokens; gpt-oss-120b costs $0.10 and $0.50. Per solved SWE-bench Verified task, GPT-5.3-Codex costs $0.59 and gpt-oss-120b $0.51.
Which has the bigger context window, GPT-5.3-Codex or gpt-oss-120b?
GPT-5.3-Codex, with 400K tokens against 131K.
How many benchmarks is the GPT-5.3-Codex vs gpt-oss-120b comparison based on?
21 benchmarks have a result for both models as of October 22, 2026. GPT-5.3-Codex'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.