R1 0528 vs GPT-4o
Updated October 21, 2026. 18 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 38.8 for GPT-4o.
GPT-4o is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 18
- R1 0528 only
- 41
- GPT-4o only
- 8
- Like-for-like categories
- 7 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 38.8.
One benchmark behind each score
Intelligence
AA Intelligence Index
No call
Only R1 0528 has a AA Intelligence Index result, 13.1.
Directional only
Web design
Design Arena: websites
R1 0528
R1 0528 leads, 1149 against 831.
Same board, both measured
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 $0.0075 per turn.
List prices
At a glance
- Coding index
- R1 0528 71.4 from 1 benchmark, GPT-4o 38.8 from 1 benchmark.
- Widest category
- Math, 70.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- AA Math Index: R1 0528 76.0 against GPT-4o 6.0, 70.0 points apart on a 0 to 100 scale.
- Output price
- R1 0528 $2.15 against GPT-4o $10.00 per million output tokens, 4.7x apart.
- Context window
- R1 0528 takes 164K tokens, GPT-4o 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 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 4 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 1 | 0 | ||
| Web design | 6 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 18 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index20
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| Aider polyglot | 71.4% | Not measured | Only R1 0528 measured |
| SWE-bench Verified | Not measured | 38.8% | Only GPT-4o measured |
| SWE-bench Lite | Not measured | 38.0% | Only GPT-4o measured |
| SWE-bench (full test set) | Not measured | 18.8% | Only GPT-4o measured |
| SWE-bench Multimodal | Not measured | 30.4% | Only GPT-4o measured |
| LiveCodeBench (Artificial Analysis run) | 77.0% | 30.9% | R1 0528 |
| Terminal-Bench Hard (Artificial Analysis run) | 15.9% | 8.3% | R1 0528 |
| WeirdML | 41.6% | Not measured | Only R1 0528 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 27 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.1 | Not measured | Only R1 0528 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 36.5% | 25.1% | R1 0528 |
| METR time horizons | 53.8% | Not measured | Only R1 0528 measured |
| GDPval | Not measured | 9.9% | Only GPT-4o measured |
| DeepResearch Bench | 35.1% | Not measured | Only R1 0528 measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 81.3% | 54.3% | R1 0528 |
| Humanity's Last Exam (Artificial Analysis run) | 15.8% | 2.4% | R1 0528 |
| GPQA Diamond (Epoch AI run) | 76.3% | Not measured | Only R1 0528 measured |
| ARC-AGI | 21.2% | 4.5% | R1 0528 |
| ARC-AGI-2 | 1.1% | 0.0% | R1 0528 |
| SimpleBench | 40.8% | Not measured | Only R1 0528 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 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| AA Math Index | 76.0 | 6.0 | R1 0528 |
| AIME 2025 (Artificial Analysis run) | 76.0% | 6.0% | R1 0528 |
| OTIS Mock AIME | 66.4% | Not measured | Only R1 0528 measured |
| MATH level 5 | 96.6% | Not measured | Only R1 0528 measured |
| 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 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 84.9% | 74.8% | R1 0528 |
| MMLU | Not measured | 88.1% | Only GPT-4o 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 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| Design Arena: websites | 1149 | 831 | R1 0528 |
| Design Arena: UI components | 1102 | 885 | R1 0528 |
| Design Arena: game dev | 1098 | 906 | R1 0528 |
| Design Arena: data viz | 1182 | 858 | R1 0528 |
| Design Arena: 3D | 1111 | 869 | R1 0528 |
| Design Arena: all code categories | 1139 | 861 | R1 0528 |
| 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 index20
| Benchmark | R1 0528 | GPT-4o | Leader |
|---|---|---|---|
| IFBench | 39.6% | 34.3% | R1 0528 |
| Long context reasoning (AA-LCR) | 55.7% | 49.3% | R1 0528 |
| DTBench | Not measured | 64.5% | Only GPT-4o measured |
| LMCA | Not measured | 16.6% | Only GPT-4o measured |
| Fiction.LiveBench | 75.0% | Not measured | Only R1 0528 measured |
| Creative writing (Lech Mazur) | 81.9% | Not measured | Only R1 0528 measured |
| 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 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | R1 0528 | GPT-4o | 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 |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | May 28, 2025 | May 13, 2024 |
| Context window | 164K | 128K |
| Input $/Mtok | $0.50 | $2.50 |
| Output $/Mtok | $2.15 | $10.00 |
| Coding index | 71.4 | 38.8 |
| 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 for coding?
Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 38.8 for GPT-4o. GPT-4o is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, R1 0528 or GPT-4o?
R1 0528 costs $0.50 per million input tokens and $2.15 per million output tokens; GPT-4o 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?
R1 0528, with 164K tokens against 128K.
How many benchmarks is the R1 0528 vs GPT-4o comparison based on?
18 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's on 1. Where only one model has a result, the page says so instead of naming a winner.