GPT-5.2 vs Grok 4.20
Updated October 21, 2026. 45 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-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 33.3 for Grok 4.20.
Pick Grok 4.20 when output tokens cost 5.6x less, or when a solved task costs $0.72 against $1.91.
- Shared results
- 45
- GPT-5.2 only
- 66
- Grok 4.20 only
- 9
- Like-for-like categories
- 8 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, six public coding benchmarks
GPT-5.2
GPT-5.2 scores 55.9 against 33.3.
3 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.2
GPT-5.2 leads, 30.4 against 25.7.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.2
GPT-5.2 leads, 91.7% against 88.6%.
Same board, both measured
Math
AIME
GPT-5.2
GPT-5.2 leads, 96.9% against 96.5%.
Same board, both measured
Knowledge
MMLU Pro
Grok 4.20
Grok 4.20 leads, 86.3% against 86.2%.
Same board, both measured
Web design
Design Arena: websites
Grok 4.20
Grok 4.20 leads, 1229 against 1195.
Same board, both measured
Long documents
Listed context window
Grok 4.20
Grok 4.20 takes 2M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Grok 4.20
GPT-5.2 $0.0088, Grok 4.20 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Grok 4.20
GPT-5.2 $1.91, Grok 4.20 $0.72.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.2 55.9 from 3 benchmarks, Grok 4.20 33.3 from 2 benchmarks.
- Widest category
- Coding, 15.1 points apart on average over 6 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): GPT-5.2 53.5% against Grok 4.20 4.1%, 49.4 points apart on a 0 to 100 scale.
- Output price
- GPT-5.2 $14.00 against Grok 4.20 $2.50 per million output tokens, 5.6x apart.
- Context window
- GPT-5.2 takes 400K tokens, Grok 4.20 2M.
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-5.2 | Bars | Grok 4.20 | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 4 | ||
| Reasoning | 3 | 3 | ||
| Math | 1 | 0 | ||
| Knowledge | 6 | 2 | ||
| Web design | 1 | 7 | ||
| General | 5 | 2 | ||
| All shared boards | 27 | 18 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| SWE-bench Verified | 72.8% | Not measured | Only GPT-5.2 measured |
| SWE-bench Multilingual | 66.7% | Not measured | Only GPT-5.2 measured |
| LMArena WebDev | 1417 | Not measured | Only GPT-5.2 measured |
| LiveCodeBench (Vals AI) | 85.4% | 84.3% | GPT-5.2 |
| SWE-bench Verified (Vals AI) | 75.8% | 72.2% | GPT-5.2 |
| Vibe Code Bench (Vals AI) | 53.5% | 4.1% | GPT-5.2 |
| Code migration (Vals AI) | Not measured | 0.3% | Only Grok 4.20 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 44.2% | Only Grok 4.20 measured |
| LiveCodeBench (Artificial Analysis run) | 89.4% | Not measured | Only GPT-5.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 37.9% | GPT-5.2 |
| Terminal-Bench | 64.9% | 57.3% | GPT-5.2 |
| GSO-Bench | 27.5% | Not measured | Only GPT-5.2 measured |
| WeirdML | 72.2% | 52.3% | GPT-5.2 |
| ALE-Bench | 1293.5 | Not measured | Only GPT-5.2 measured |
| LMArena Text: coding | 1442 | Not measured | Only GPT-5.2 measured |
| LMArena Text: software and IT | 1434 | Not measured | Only GPT-5.2 measured |
| LMArena WebDev: HTML | 1427 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 25.7 | GPT-5.2 |
| Epoch Capabilities Index | 153.7 | 152.1 | GPT-5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1086 | 1144 | Grok 4.20 |
| Design Arena: agents building full-stack apps | 1043 | 1054 | Grok 4.20 |
| Design Arena: agents building mobile apps | 1093 | 1090 | GPT-5.2 |
| Design Arena: agents building Android apps | 1066 | 1052 | GPT-5.2 |
| Design Arena: agents building Godot games | 1142 | 1089 | GPT-5.2 |
| Design Arena: HTML slides | Not measured | 1180 | Only Grok 4.20 measured |
| Finance Agent (Vals AI) | Not measured | 28.5% | Only Grok 4.20 measured |
| Tax Agent Bench (Vals AI) | Not measured | 7.0% | Only Grok 4.20 measured |
| Legal Research Bench (Vals AI) | Not measured | 13.9% | Only Grok 4.20 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 11.7% | Only Grok 4.20 measured |
| τ²-Bench Telecom | 84.8% | 93.0% | Grok 4.20 |
| METR time horizons | 75.3% | Not measured | Only GPT-5.2 measured |
| Remote Labor Index | 2.5% | Not measured | Only GPT-5.2 measured |
| GDPval | 49.7% | Not measured | Only GPT-5.2 measured |
| DeepResearch Bench | 41.1% | Not measured | Only GPT-5.2 measured |
| Vending-Bench 2 | $3,591 | $4,663 | Grok 4.20 |
| Neither model has a result on the other 23 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | 88.6% | GPT-5.2 |
| MMMU Pro (Vals AI) | 86.7% | 83.5% | GPT-5.2 |
| GPQA Diamond (Artificial Analysis run) | 90.3% | 91.1% | Grok 4.20 |
| Humanity's Last Exam (Artificial Analysis run) | 37.7% | 34.5% | GPT-5.2 |
| GPQA Diamond (Epoch AI run) | 91.4% | Not measured | Only GPT-5.2 measured |
| ARC-AGI | 86.2% | 89.5% | Grok 4.20 |
| ARC-AGI-2 | 52.9% | 65.1% | Grok 4.20 |
| SimpleBench | 45.8% | Not measured | Only GPT-5.2 measured |
| Chess puzzles | 48.0% | Not measured | Only GPT-5.2 measured |
| Mystery game puzzles | 23.0% | Not measured | Only GPT-5.2 measured |
| EBR-bench | 23.0% | Not measured | Only GPT-5.2 measured |
| VPCT | 84.0% | Not measured | Only GPT-5.2 measured |
| LMArena Text: hard prompts | 1428 | Not measured | Only GPT-5.2 measured |
| LMArena Text: expert | 1445 | Not measured | Only GPT-5.2 measured |
| LMArena Text: hard prompts in English | 1431 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: diagrams | 1265 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: homework | 1276 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| AIME | 96.9% | 96.5% | GPT-5.2 |
| MGSM (Vals AI) | 94.0% | Not measured | Only GPT-5.2 measured |
| AA Math Index | 99.0 | Not measured | Only GPT-5.2 measured |
| AIME 2025 (Artificial Analysis run) | 99.0% | Not measured | Only GPT-5.2 measured |
| OTIS Mock AIME | 96.1% | Not measured | Only GPT-5.2 measured |
| FrontierMath, tiers 1 to 3 | 67.4% | Not measured | Only GPT-5.2 measured |
| FrontierMath, tier 4 | 31.7% | Not measured | Only GPT-5.2 measured |
| ProofBench | 15.0% | Not measured | Only GPT-5.2 measured |
| LMArena Text: math | 1440 | Not measured | Only GPT-5.2 measured |
| LMArena Text: mathematical work | 1442 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 86.3% | Grok 4.20 |
| LegalBench (Vals AI) | 82.8% | 77.7% | GPT-5.2 |
| CaseLaw (Vals AI) | 66.0% | 54.4% | GPT-5.2 |
| CorpFin (Vals AI) | 65.9% | 63.7% | GPT-5.2 |
| TaxEval (Vals AI) | 75.8% | 74.1% | GPT-5.2 |
| MortgageTax (Vals AI) | 67.1% | 45.4% | GPT-5.2 |
| MedQA (Vals AI) | 94.1% | 94.5% | Grok 4.20 |
| MedCode (Vals AI) | 49.8% | 32.2% | GPT-5.2 |
| MMLU Pro (Artificial Analysis run) | 87.4% | Not measured | Only GPT-5.2 measured |
| SimpleQA Verified | 37.1% | Not measured | Only GPT-5.2 measured |
| LMArena Text: science | 1425 | Not measured | Only GPT-5.2 measured |
| LMArena Text: medicine and healthcare | 1425 | Not measured | Only GPT-5.2 measured |
| LMArena Text: legal and government | 1427 | Not measured | Only GPT-5.2 measured |
| LMArena Text: business and finance | 1414 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| Design Arena: websites | 1195 | 1229 | Grok 4.20 |
| Design Arena: UI components | 1190 | 1199 | Grok 4.20 |
| Design Arena: game dev | 1195 | 1192 | GPT-5.2 |
| Design Arena: data viz | 1202 | 1217 | Grok 4.20 |
| Design Arena: 3D | 1079 | 1193 | Grok 4.20 |
| Design Arena: all code categories | 1170 | 1221 | Grok 4.20 |
| Design Arena: SVG | 1139 | 1164 | Grok 4.20 |
| Design Arena: ASCII art | 1152 | 1174 | Grok 4.20 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | GPT-5.2 | Grok 4.20 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.3% | 38.2% | GPT-5.2 |
| MedScribe (Vals AI) | 84.4% | 63.4% | GPT-5.2 |
| Vals Multimodal Index | Not measured | 39.1% | Only Grok 4.20 measured |
| IFBench | 75.4% | 81.2% | Grok 4.20 |
| Long context reasoning (AA-LCR) | 82.7% | 69.0% | GPT-5.2 |
| DTBench | 90.9% | 90.1% | GPT-5.2 |
| LMCA | 43.9% | 38.7% | GPT-5.2 |
| CL-bench | 18.2% | 22.2% | Grok 4.20 |
| Furniture assembly | 38.3% | Not measured | Only GPT-5.2 measured |
| CL-bench Life | Not measured | 11.9% | Only Grok 4.20 measured |
| LMArena Text | 1416 | Not measured | Only GPT-5.2 measured |
| LMArena Text: instruction following | 1409 | Not measured | Only GPT-5.2 measured |
| LMArena Text: creative writing | 1376 | Not measured | Only GPT-5.2 measured |
| LMArena Vision | 1246 | Not measured | Only GPT-5.2 measured |
| LMArena Text: English | 1422 | Not measured | Only GPT-5.2 measured |
| LMArena Text: non-English | 1405 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Chinese | 1447 | Not measured | Only GPT-5.2 measured |
| LMArena Text: German | 1444 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Japanese | 1420 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Korean | 1374 | Not measured | Only GPT-5.2 measured |
| LMArena Text: French | 1454 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Spanish | 1413 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Russian | 1415 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Polish | 1426 | Not measured | Only GPT-5.2 measured |
| LMArena Text: multi-turn | 1419 | Not measured | Only GPT-5.2 measured |
| LMArena Text: longer queries | 1413 | Not measured | Only GPT-5.2 measured |
| LMArena Text: writing and language | 1392 | Not measured | Only GPT-5.2 measured |
| LMArena Text: entertainment and media | 1378 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: English | 1243 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: Chinese | 1305 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: reading text | 1257 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: humor | 1227 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: captioning | 1267 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: recognizing things | 1232 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: creative writing | 1225 | Not measured | Only GPT-5.2 measured |
| LMArena Document | 1405 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2 | Grok 4.20 | 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
Grok 4.20 costs less
Repository review
50K input + 3K output tokens
Grok 4.20 costs less
Agent loop
200K input + 10K output tokens
Grok 4.20 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-5.2 | SpaceXAI Grok 4.20 |
|---|---|---|
| Maker | OpenAI | xAI |
| Weights | No public weights listed | No public weights listed |
| Released | December 10, 2025 | March 31, 2026 |
| Context window | 400K | 2M |
| Input $/Mtok | $1.75 | $1.25 |
| Output $/Mtok | $14.00 | $2.50 |
| Coding index | 55.9 | 33.3 |
| Independent measurements behind it | 3 | 2 |
| Cost per solved task | $1.91 | $0.72 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2 better than Grok 4.20 for coding?
Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 33.3 for Grok 4.20. Pick Grok 4.20 when output tokens cost 5.6x less, or when a solved task costs $0.72 against $1.91.
Which is cheaper, GPT-5.2 or Grok 4.20?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Per solved SWE-bench Verified task, GPT-5.2 costs $1.91 and Grok 4.20 $0.72.
Which has the bigger context window, GPT-5.2 or Grok 4.20?
Grok 4.20, with 2M tokens against 400K.
How many benchmarks is the GPT-5.2 vs Grok 4.20 comparison based on?
45 benchmarks have a result for both models as of October 21, 2026. GPT-5.2's coding index rests on 3 independent benchmarks and Grok 4.20's on 2. Where only one model has a result, the page says so instead of naming a winner.