R1 0528 vs GPT-4o (2024-11-20)
Updated October 21, 2026. 7 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 18.2 for GPT-4o (2024-11-20).
GPT-4o (2024-11-20) is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 7
- R1 0528 only
- 52
- GPT-4o (2024-11-20) only
- 17
- Like-for-like categories
- 5 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
R1 0528
R1 0528 scores 71.4 against 18.2.
One benchmark behind each score
Intelligence
AA Intelligence Index
R1 0528
R1 0528 leads, 13.1 against 8.4.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-4o (2024-11-20) has a GPQA Diamond result, 53.8%.
Directional only
Math
AIME
No call
Only GPT-4o (2024-11-20) has a AIME result, 11.9%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-4o (2024-11-20) has a MMLU Pro result, 72.6%.
Directional only
Web design
Design Arena: websites
No call
Only R1 0528 has a Design Arena: websites result, 1149.
Directional only
Long documents
Listed context window
R1 0528
R1 0528 takes 164K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
R1 0528
R1 0528 $0.0016, GPT-4o (2024-11-20) $0.0075 per turn.
List prices
At a glance
- Coding index
- R1 0528 71.4 from 1 benchmark, GPT-4o (2024-11-20) 18.2 from 1 benchmark.
- Widest category
- Math, 53.5 points apart on average over 2 shared benchmarks.
- Widest single gap
- OTIS Mock AIME: R1 0528 66.4% against GPT-4o (2024-11-20) 6.3%, 60.1 points apart on a 0 to 100 scale.
- Output price
- R1 0528 $2.15 against GPT-4o (2024-11-20) $10.00 per million output tokens, 4.7x apart.
- Context window
- R1 0528 takes 164K tokens, GPT-4o (2024-11-20) 128K.
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 | R1 0528 | Bars | GPT-4o (2024-11-20) | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 0 | ||
| Math | 2 | 0 | ||
| General | 1 | 0 | ||
| All shared boards | 7 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index20
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| Aider polyglot | 71.4% | 18.2% | R1 0528 |
| LiveCodeBench (Vals AI) | Not measured | 43.4% | Only GPT-4o (2024-11-20) measured |
| LiveCodeBench (Artificial Analysis run) | 77.0% | Not measured | Only R1 0528 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 15.9% | Not measured | Only R1 0528 measured |
| GSO-Bench | Not measured | 0.0% | Only GPT-4o (2024-11-20) measured |
| WeirdML | 41.6% | 25.1% | R1 0528 |
| Cybench | Not measured | 12.5% | Only GPT-4o (2024-11-20) measured |
| ALE-Bench | 804.1 | Not measured | Only R1 0528 measured |
| LMArena Text: coding | 1427 | Not measured | Only R1 0528 measured |
| LMArena Text: software and IT | 1435 | Not measured | Only R1 0528 measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.1 | 8.4 | R1 0528 |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 36.5% | Not measured | Only R1 0528 measured |
| METR time horizons | 53.8% | Not measured | Only R1 0528 measured |
| DeepResearch Bench | 35.1% | Not measured | Only R1 0528 measured |
| TheAgentCompany | Not measured | 8.6% | Only GPT-4o (2024-11-20) measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 53.8% | Only GPT-4o (2024-11-20) measured |
| MMMU Pro (Vals AI) | Not measured | 62.2% | Only GPT-4o (2024-11-20) measured |
| GPQA Diamond (Artificial Analysis run) | 81.3% | Not measured | Only R1 0528 measured |
| Humanity's Last Exam (Artificial Analysis run) | 15.8% | Not measured | Only R1 0528 measured |
| GPQA Diamond (Epoch AI run) | 76.3% | 47.9% | R1 0528 |
| ARC-AGI | 21.2% | Not measured | Only R1 0528 measured |
| ARC-AGI-2 | 1.1% | Not measured | Only R1 0528 measured |
| SimpleBench | 40.8% | Not measured | Only R1 0528 measured |
| VPCT | Not measured | 40.0% | Only GPT-4o (2024-11-20) measured |
| LMArena Text: hard prompts | 1415 | Not measured | Only R1 0528 measured |
| LMArena Text: expert | 1394 | Not measured | Only R1 0528 measured |
| LMArena Text: hard prompts in English | 1422 | Not measured | Only R1 0528 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| AIME | Not measured | 11.9% | Only GPT-4o (2024-11-20) measured |
| MATH 500 (Vals AI) | Not measured | 74.0% | Only GPT-4o (2024-11-20) measured |
| MGSM (Vals AI) | Not measured | 90.4% | Only GPT-4o (2024-11-20) measured |
| AA Math Index | 76.0 | Not measured | Only R1 0528 measured |
| AIME 2025 (Artificial Analysis run) | 76.0% | Not measured | Only R1 0528 measured |
| OTIS Mock AIME | 66.4% | 6.3% | R1 0528 |
| MATH level 5 | 96.6% | 49.8% | R1 0528 |
| LMArena Text: math | 1400 | Not measured | Only R1 0528 measured |
| LMArena Text: mathematical work | 1415 | Not measured | Only R1 0528 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 | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 72.6% | Only GPT-4o (2024-11-20) measured |
| LegalBench (Vals AI) | Not measured | 82.2% | Only GPT-4o (2024-11-20) measured |
| CaseLaw (Vals AI) | Not measured | 59.7% | Only GPT-4o (2024-11-20) measured |
| CorpFin (Vals AI) | Not measured | 45.9% | Only GPT-4o (2024-11-20) measured |
| TaxEval (Vals AI) | Not measured | 74.5% | Only GPT-4o (2024-11-20) measured |
| MortgageTax (Vals AI) | Not measured | 57.4% | Only GPT-4o (2024-11-20) measured |
| MMLU Pro (Artificial Analysis run) | 84.9% | Not measured | Only R1 0528 measured |
| GeoBench | Not measured | 71.0% | Only GPT-4o (2024-11-20) measured |
| LMArena Text: science | 1430 | Not measured | Only R1 0528 measured |
| LMArena Text: medicine and healthcare | 1445 | Not measured | Only R1 0528 measured |
| LMArena Text: legal and government | 1419 | Not measured | Only R1 0528 measured |
| LMArena Text: business and finance | 1402 | Not measured | Only R1 0528 measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| Design Arena: websites | 1149 | Not measured | Only R1 0528 measured |
| Design Arena: UI components | 1102 | Not measured | Only R1 0528 measured |
| Design Arena: game dev | 1098 | Not measured | Only R1 0528 measured |
| Design Arena: data viz | 1182 | Not measured | Only R1 0528 measured |
| Design Arena: 3D | 1111 | Not measured | Only R1 0528 measured |
| Design Arena: all code categories | 1139 | Not measured | Only R1 0528 measured |
| Design Arena: SVG | 1038 | Not measured | Only R1 0528 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | Leader |
|---|---|---|---|
| IFBench | 39.6% | Not measured | Only R1 0528 measured |
| Long context reasoning (AA-LCR) | 55.7% | Not measured | Only R1 0528 measured |
| Fiction.LiveBench | 75.0% | Not measured | Only R1 0528 measured |
| Creative writing (Lech Mazur) | 81.9% | 81.8% | R1 0528 |
| LMArena Text | 1428 | Not measured | Only R1 0528 measured |
| LMArena Text: instruction following | 1382 | Not measured | Only R1 0528 measured |
| LMArena Text: creative writing | 1405 | Not measured | Only R1 0528 measured |
| LMArena Text: English | 1437 | Not measured | Only R1 0528 measured |
| LMArena Text: non-English | 1412 | Not measured | Only R1 0528 measured |
| LMArena Text: Chinese | 1442 | Not measured | Only R1 0528 measured |
| LMArena Text: German | 1404 | Not measured | Only R1 0528 measured |
| LMArena Text: Japanese | 1391 | Not measured | Only R1 0528 measured |
| LMArena Text: Korean | 1360 | Not measured | Only R1 0528 measured |
| LMArena Text: French | 1417 | Not measured | Only R1 0528 measured |
| LMArena Text: Spanish | 1411 | Not measured | Only R1 0528 measured |
| LMArena Text: Russian | 1423 | Not measured | Only R1 0528 measured |
| LMArena Text: Polish | 1428 | Not measured | Only R1 0528 measured |
| LMArena Text: multi-turn | 1405 | Not measured | Only R1 0528 measured |
| LMArena Text: longer queries | 1391 | Not measured | Only R1 0528 measured |
| LMArena Text: writing and language | 1402 | Not measured | Only R1 0528 measured |
| LMArena Text: entertainment and media | 1400 | Not measured | Only R1 0528 measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | R1 0528 | GPT-4o (2024-11-20) | 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
R1 0528 costs less
Repository review
50K input + 3K output tokens
R1 0528 costs less
Agent loop
200K input + 10K output tokens
R1 0528 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 | DeepSeek R1 0528 | OpenAI GPT-4o (2024-11-20) |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | May 28, 2025 | November 20, 2024 |
| Context window | 164K | 128K |
| Input $/Mtok | $0.50 | $2.50 |
| Output $/Mtok | $2.15 | $10.00 |
| Coding index | 71.4 | 18.2 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is R1 0528 better than GPT-4o (2024-11-20) for coding?
Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 18.2 for GPT-4o (2024-11-20). GPT-4o (2024-11-20) is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, R1 0528 or GPT-4o (2024-11-20)?
R1 0528 costs $0.50 per million input tokens and $2.15 per million output tokens; GPT-4o (2024-11-20) costs $2.50 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, R1 0528 or GPT-4o (2024-11-20)?
R1 0528, with 164K tokens against 128K.
How many benchmarks is the R1 0528 vs GPT-4o (2024-11-20) comparison based on?
7 benchmarks have a result for both models as of October 21, 2026. R1 0528's coding index rests on 1 independent benchmark and GPT-4o (2024-11-20)'s on 1. Where only one model has a result, the page says so instead of naming a winner.