GPT-5.3-Codex vs Llama 4 Scout
Updated October 21, 2026. 14 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GPT-5.3-Codex for coding: it scores 29.5 on the Vibe Coding Index against 9.1 for Llama 4 Scout.
Pick Llama 4 Scout when output tokens cost 46.7x less, or when the context window is larger, 1.31M against 400K tokens.
- Shared results
- 14
- GPT-5.3-Codex only
- 20
- Llama 4 Scout only
- 66
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
GPT-5.3-Codex
GPT-5.3-Codex scores 29.5 against 9.1.
One benchmark behind each score
Intelligence
AA Intelligence Index
GPT-5.3-Codex
GPT-5.3-Codex leads, 32.5 against 6.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Llama 4 Scout has a AA Agentic Index result, 0.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Llama 4 Scout has a GPQA Diamond result, 47.0%.
Directional only
Math
AIME
No call
Only Llama 4 Scout has a AIME result, 19.0%.
Directional only
Knowledge
MMLU Pro
No call
Only Llama 4 Scout has a MMLU Pro result, 69.6%.
Directional only
Web design
Design Arena: websites
GPT-5.3-Codex
GPT-5.3-Codex leads, 1163 against 750.
Same board, both measured
Long documents
Listed context window
Llama 4 Scout
Llama 4 Scout takes 1.31M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Scout
GPT-5.3-Codex $0.0088, Llama 4 Scout $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.3-Codex
GPT-5.3-Codex $0.59, Llama 4 Scout $1.276.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.3-Codex 29.5 from 1 benchmark, Llama 4 Scout 9.1 from 1 benchmark.
- Widest category
- Agentic work, 70.5 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GPT-5.3-Codex 86.0% against Llama 4 Scout 15.5%, 70.5 points apart on a 0 to 100 scale.
- Output price
- GPT-5.3-Codex $14.00 against Llama 4 Scout $0.30 per million output tokens, 46.7x apart.
- Context window
- GPT-5.3-Codex takes 400K tokens, Llama 4 Scout 1.31M.
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 | Llama 4 Scout | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| Web design | 5 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 14 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index20
| Benchmark | GPT-5.3-Codex | Llama 4 Scout | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 9.1% | Only Llama 4 Scout measured |
| LMArena WebDev | 1407 | Not measured | Only GPT-5.3-Codex measured |
| AA Coding Index | Not measured | 8.2 | Only Llama 4 Scout measured |
| LiveCodeBench (Vals AI) | 87.3% | 38.5% | GPT-5.3-Codex |
| SWE-bench Verified (Vals AI) | 78.0% | Not measured | Only GPT-5.3-Codex measured |
| 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 | 29.9% | Only Llama 4 Scout measured |
| SciCode | Not measured | 21.3% | Only Llama 4 Scout measured |
| Terminal-Bench Hard (Artificial Analysis run) | 53.0% | 1.5% | GPT-5.3-Codex |
| Terminal-Bench | 78.4% | Not measured | Only GPT-5.3-Codex measured |
| WeirdML | 79.3% | Not measured | Only GPT-5.3-Codex measured |
| ALE-Bench | 1655.2 | Not measured | Only GPT-5.3-Codex measured |
| LMArena Text: coding | Not measured | 1286 | Only Llama 4 Scout measured |
| LMArena Text: software and IT | Not measured | 1286 | Only Llama 4 Scout 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 |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.3-Codex | Llama 4 Scout | Leader |
|---|---|---|---|
| AA Intelligence Index | 32.5 | 6.5 | GPT-5.3-Codex |
| Epoch Capabilities Index | 157.1 | 129.6 | GPT-5.3-Codex |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.3-Codex | Llama 4 Scout | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.5 | Only Llama 4 Scout measured |
| Design Arena: agents building web apps | 1033 | 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 | 1054 | 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% | 15.5% | GPT-5.3-Codex |
| METR time horizons | 74.5% | Not measured | Only GPT-5.3-Codex measured |
| Vending-Bench 2 | $5,940 | Not measured | Only GPT-5.3-Codex 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 | Llama 4 Scout | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 47.0% | Only Llama 4 Scout measured |
| MMMU Pro (Vals AI) | Not measured | 58.8% | Only Llama 4 Scout measured |
| GPQA Diamond (Artificial Analysis run) | 91.5% | 58.7% | GPT-5.3-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 42.5% | 3.8% | GPT-5.3-Codex |
| GPQA Diamond (Epoch AI run) | Not measured | 51.8% | Only Llama 4 Scout measured |
| ARC-AGI | Not measured | 0.5% | Only Llama 4 Scout measured |
| ARC-AGI-2 | Not measured | 0.0% | Only Llama 4 Scout measured |
| LMArena Text: hard prompts | Not measured | 1266 | Only Llama 4 Scout measured |
| LMArena Text: expert | Not measured | 1235 | Only Llama 4 Scout measured |
| LMArena Text: hard prompts in English | Not measured | 1293 | Only Llama 4 Scout measured |
| LMArena Vision: diagrams | Not measured | 1125 | Only Llama 4 Scout measured |
| LMArena Vision: homework | Not measured | 1148 | Only Llama 4 Scout measured |
| Neither model has a result on the other 9 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-5.3-Codex | Llama 4 Scout | Leader |
|---|---|---|---|
| AIME | Not measured | 19.0% | Only Llama 4 Scout measured |
| MATH 500 (Vals AI) | Not measured | 79.2% | Only Llama 4 Scout measured |
| MGSM (Vals AI) | Not measured | 88.0% | Only Llama 4 Scout measured |
| AA Math Index | Not measured | 14.0 | Only Llama 4 Scout measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 14.0% | Only Llama 4 Scout measured |
| OTIS Mock AIME | Not measured | 7.8% | Only Llama 4 Scout measured |
| MATH level 5 | Not measured | 62.3% | Only Llama 4 Scout measured |
| LMArena Text: math | Not measured | 1287 | Only Llama 4 Scout measured |
| LMArena Text: mathematical work | Not measured | 1286 | Only Llama 4 Scout measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | GPT-5.3-Codex | Llama 4 Scout | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 69.6% | Only Llama 4 Scout measured |
| LegalBench (Vals AI) | Not measured | 72.0% | Only Llama 4 Scout measured |
| CorpFin (Vals AI) | Not measured | 46.8% | Only Llama 4 Scout measured |
| TaxEval (Vals AI) | Not measured | 55.2% | Only Llama 4 Scout measured |
| MortgageTax (Vals AI) | Not measured | 57.8% | Only Llama 4 Scout measured |
| MedQA (Vals AI) | Not measured | 50.9% | Only Llama 4 Scout measured |
| MedCode (Vals AI) | Not measured | 23.3% | Only Llama 4 Scout measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 75.2% | Only Llama 4 Scout measured |
| LMArena Text: science | Not measured | 1278 | Only Llama 4 Scout measured |
| LMArena Text: medicine and healthcare | Not measured | 1275 | Only Llama 4 Scout measured |
| LMArena Text: legal and government | Not measured | 1285 | Only Llama 4 Scout measured |
| LMArena Text: business and finance | Not measured | 1257 | Only Llama 4 Scout measured |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GPT-5.3-Codex | Llama 4 Scout | Leader |
|---|---|---|---|
| Design Arena: websites | 1163 | 750 | GPT-5.3-Codex |
| Design Arena: UI components | 1137 | 767 | GPT-5.3-Codex |
| Design Arena: game dev | 1162 | 773 | GPT-5.3-Codex |
| Design Arena: data viz | 1164 | 896 | GPT-5.3-Codex |
| Design Arena: 3D | 1008 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: all code categories | 1145 | 790 | GPT-5.3-Codex |
| Design Arena: SVG | 1129 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: ASCII art | 1151 | 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 | Llama 4 Scout | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 34.8% | Only Llama 4 Scout measured |
| MedScribe (Vals AI) | Not measured | 50.6% | Only Llama 4 Scout measured |
| IFBench | 75.4% | 39.5% | GPT-5.3-Codex |
| Long context reasoning (AA-LCR) | 83.3% | 27.7% | GPT-5.3-Codex |
| DTBench | Not measured | 57.9% | Only Llama 4 Scout measured |
| LMCA | Not measured | 12.0% | Only Llama 4 Scout measured |
| Fiction.LiveBench | Not measured | 36.0% | Only Llama 4 Scout measured |
| LMArena Text | Not measured | 1279 | Only Llama 4 Scout measured |
| LMArena Text: instruction following | Not measured | 1248 | Only Llama 4 Scout measured |
| LMArena Text: creative writing | Not measured | 1249 | Only Llama 4 Scout measured |
| LMArena Vision | Not measured | 1118 | Only Llama 4 Scout measured |
| LMArena Text: English | Not measured | 1304 | Only Llama 4 Scout measured |
| LMArena Text: non-English | Not measured | 1252 | Only Llama 4 Scout measured |
| LMArena Text: Chinese | Not measured | 1255 | Only Llama 4 Scout measured |
| LMArena Text: German | Not measured | 1273 | Only Llama 4 Scout measured |
| LMArena Text: Japanese | Not measured | 1206 | Only Llama 4 Scout measured |
| LMArena Text: Korean | Not measured | 1207 | Only Llama 4 Scout measured |
| LMArena Text: French | Not measured | 1283 | Only Llama 4 Scout measured |
| LMArena Text: Spanish | Not measured | 1278 | Only Llama 4 Scout measured |
| LMArena Text: Russian | Not measured | 1263 | Only Llama 4 Scout measured |
| LMArena Text: Polish | Not measured | 1265 | Only Llama 4 Scout measured |
| LMArena Text: multi-turn | Not measured | 1280 | Only Llama 4 Scout measured |
| LMArena Text: longer queries | Not measured | 1265 | Only Llama 4 Scout measured |
| LMArena Text: writing and language | Not measured | 1269 | Only Llama 4 Scout measured |
| LMArena Text: entertainment and media | Not measured | 1242 | Only Llama 4 Scout measured |
| LMArena Vision: English | Not measured | 1143 | Only Llama 4 Scout measured |
| LMArena Vision: Chinese | Not measured | 1106 | Only Llama 4 Scout measured |
| LMArena Vision: reading text | Not measured | 1117 | Only Llama 4 Scout measured |
| LMArena Vision: humor | Not measured | 1102 | Only Llama 4 Scout measured |
| LMArena Vision: creative writing | Not measured | 1126 | Only Llama 4 Scout measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.3-Codex | Llama 4 Scout | 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
Llama 4 Scout costs less
Repository review
50K input + 3K output tokens
Llama 4 Scout costs less
Agent loop
200K input + 10K output tokens
Llama 4 Scout 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 | Meta Llama 4 Scout |
|---|---|---|
| Maker | OpenAI | Meta Llama |
| Weights | No public weights listed | Open weights |
| Released | February 24, 2026 | April 5, 2025 |
| Context window | 400K | 1.31M |
| Input $/Mtok | $1.75 | $0.10 |
| Output $/Mtok | $14.00 | $0.30 |
| Coding index | 29.5 | 9.1 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.59 | $1.276 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.3-Codex better than Llama 4 Scout for coding?
Pick GPT-5.3-Codex for coding: it scores 29.5 on the Vibe Coding Index against 9.1 for Llama 4 Scout. Pick Llama 4 Scout when output tokens cost 46.7x less, or when the context window is larger, 1.31M against 400K tokens.
Which is cheaper, GPT-5.3-Codex or Llama 4 Scout?
GPT-5.3-Codex costs $1.75 per million input tokens and $14.00 per million output tokens; Llama 4 Scout costs $0.10 and $0.30. Per solved SWE-bench Verified task, GPT-5.3-Codex costs $0.59 and Llama 4 Scout $1.276.
Which has the bigger context window, GPT-5.3-Codex or Llama 4 Scout?
Llama 4 Scout, with 1.31M tokens against 400K.
How many benchmarks is the GPT-5.3-Codex vs Llama 4 Scout comparison based on?
14 benchmarks have a result for both models as of October 21, 2026. GPT-5.3-Codex's coding index rests on 1 independent benchmark and Llama 4 Scout's on 1. Where only one model has a result, the page says so instead of naming a winner.