DeepSeek V3 0324 vs Grok 4.20
Grok 4.20 leads DeepSeek V3 0324 on the Artificial Analysis Intelligence Index, 25.7 to 9.7, and DeepSeek V3 0324 costs 2.3x less per output token ($1.07 vs $2.50 per million). Updated October 22, 2026; 18 benchmarks have a result for both.
DeepSeek V3 0324 or Grok 4.20: which to pick
Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; DeepSeek V3 0324 has none, so the two cannot be ranked on coding.
Pick DeepSeek V3 0324 for output tokens 2.3x cheaper ($1.07 vs $2.50 per million).
- Shared results
- 18
- DeepSeek V3 0324 only
- 17
- Grok 4.20 only
- 37
- Like-for-like categories
- 7 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 Grok 4.20 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Grok 4.20
Grok 4.20 leads, 25.7 against 9.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V3 0324 has a AA Agentic Index result, 0.8.
Directional only
Reasoning
GPQA Diamond
Grok 4.20
Grok 4.20 leads, 88.6% against 61.6%.
Same board, both measured
Math
AIME
Grok 4.20
Grok 4.20 leads, 96.5% against 52.2%.
Same board, both measured
Knowledge
MMLU Pro
Grok 4.20
Grok 4.20 leads, 86.3% against 79.5%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Grok 4.20 has a Design Arena: websites result, 1229.
Directional only
Long documents
Listed context window
Grok 4.20
Grok 4.20 takes 2M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3 0324
DeepSeek V3 0324 $0.0008, Grok 4.20 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Grok 4.20 has the number, $0.72.
Directional only
At a glance
- Coding index
- DeepSeek V3 0324 not benchmarked, Grok 4.20 33.3 from 2 benchmarks.
- Widest category
- Agentic work, 45.9 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: DeepSeek V3 0324 47.1% against Grok 4.20 93.0%, 45.9 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3 0324 $1.07 against Grok 4.20 $2.50 per million output tokens, 2.3x apart.
- Context window
- DeepSeek V3 0324 takes 164K 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 | DeepSeek V3 0324 | Bars | Grok 4.20 | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 5 | ||
| General | 0 | 4 | ||
| All shared boards | 0 | 18 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| SWE-bench Verified | 42.0% | Not measured | Only DeepSeek V3 0324 measured |
| AA Coding Index | 21.2 | Not measured | Only DeepSeek V3 0324 measured |
| LiveCodeBench (Vals AI) | 65.5% | 84.3% | Grok 4.20 |
| SWE-bench Verified (Vals AI) | Not measured | 72.2% | Only Grok 4.20 measured |
| Vibe Code Bench (Vals AI) | Not measured | 4.1% | Only Grok 4.20 measured |
| 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) | 40.5% | Not measured | Only DeepSeek V3 0324 measured |
| SciCode | 39.0% | Not measured | Only DeepSeek V3 0324 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 15.2% | 37.9% | Grok 4.20 |
| Terminal-Bench | Not measured | 57.3% | Only Grok 4.20 measured |
| WeirdML | 36.1% | 52.3% | Grok 4.20 |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.7 | 25.7 | Grok 4.20 |
| Epoch Capabilities Index | Not measured | 152.1 | Only Grok 4.20 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | Not measured | Only DeepSeek V3 0324 measured |
| Design Arena: agents building web apps | Not measured | 1144 | Only Grok 4.20 measured |
| Design Arena: agents building full-stack apps | Not measured | 1054 | Only Grok 4.20 measured |
| Design Arena: agents building mobile apps | Not measured | 1090 | Only Grok 4.20 measured |
| Design Arena: agents building Android apps | Not measured | 1045 | Only Grok 4.20 measured |
| Design Arena: agents building Godot games | Not measured | 1089 | Only Grok 4.20 measured |
| 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 | 47.1% | 93.0% | Grok 4.20 |
| METR time horizons | 49.6% | Not measured | Only DeepSeek V3 0324 measured |
| Vending-Bench 2 | Not measured | $4,663 | Only Grok 4.20 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| GPQA Diamond | 61.6% | 88.6% | Grok 4.20 |
| MMMU Pro (Vals AI) | Not measured | 83.5% | Only Grok 4.20 measured |
| GPQA Diamond (Artificial Analysis run) | 65.5% | 91.1% | Grok 4.20 |
| Humanity's Last Exam (Artificial Analysis run) | 4.7% | 34.5% | Grok 4.20 |
| GPQA Diamond (Epoch AI run) | 67.6% | Not measured | Only DeepSeek V3 0324 measured |
| ARC-AGI | Not measured | 89.5% | Only Grok 4.20 measured |
| ARC-AGI-2 | Not measured | 65.1% | Only Grok 4.20 measured |
| SimpleBench | 27.2% | Not measured | Only DeepSeek V3 0324 measured |
| Kagi LLM Benchmark | Not measured | 75.0% | Only Grok 4.20 measured |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| AIME | 52.2% | 96.5% | Grok 4.20 |
| MATH 500 (Vals AI) | 88.6% | Not measured | Only DeepSeek V3 0324 measured |
| MGSM (Vals AI) | 91.7% | Not measured | Only DeepSeek V3 0324 measured |
| AA Math Index | 41.0 | Not measured | Only DeepSeek V3 0324 measured |
| AIME 2025 (Artificial Analysis run) | 41.0% | Not measured | Only DeepSeek V3 0324 measured |
| OTIS Mock AIME | 37.8% | Not measured | Only DeepSeek V3 0324 measured |
| MATH level 5 | 75.5% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| MMLU Pro | 79.5% | 86.3% | Grok 4.20 |
| LegalBench (Vals AI) | 77.7% | 77.7% | Grok 4.20 |
| CaseLaw (Vals AI) | Not measured | 54.4% | Only Grok 4.20 measured |
| CorpFin (Vals AI) | 54.7% | 63.7% | Grok 4.20 |
| TaxEval (Vals AI) | 71.1% | 74.1% | Grok 4.20 |
| MortgageTax (Vals AI) | Not measured | 45.4% | Only Grok 4.20 measured |
| MedQA (Vals AI) | 82.0% | 94.5% | Grok 4.20 |
| MedCode (Vals AI) | Not measured | 32.2% | Only Grok 4.20 measured |
| MMLU Pro (Artificial Analysis run) | 81.9% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1229 | Only Grok 4.20 measured |
| Design Arena: UI components | Not measured | 1200 | Only Grok 4.20 measured |
| Design Arena: game dev | Not measured | 1193 | Only Grok 4.20 measured |
| Design Arena: data viz | Not measured | 1217 | Only Grok 4.20 measured |
| Design Arena: 3D | Not measured | 1193 | Only Grok 4.20 measured |
| Design Arena: all code categories | Not measured | 1221 | Only Grok 4.20 measured |
| Design Arena: SVG | Not measured | 1165 | Only Grok 4.20 measured |
| Design Arena: ASCII art | Not measured | 1175 | Only Grok 4.20 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3 0324 | Grok 4.20 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 38.2% | Only Grok 4.20 measured |
| MedScribe (Vals AI) | Not measured | 63.4% | Only Grok 4.20 measured |
| Vals Multimodal Index | Not measured | 39.1% | Only Grok 4.20 measured |
| IFBench | 41.0% | 81.2% | Grok 4.20 |
| Long context reasoning (AA-LCR) | 40.7% | 69.0% | Grok 4.20 |
| DTBench | 64.8% | 90.1% | Grok 4.20 |
| LMCA | 15.5% | 38.7% | Grok 4.20 |
| Fiction.LiveBench | 50.0% | Not measured | Only DeepSeek V3 0324 measured |
| Creative writing (Lech Mazur) | 77.0% | Not measured | Only DeepSeek V3 0324 measured |
| CL-bench | Not measured | 22.2% | Only Grok 4.20 measured |
| CL-bench Life | Not measured | 11.9% | Only Grok 4.20 measured |
| Neither model has a result on the other 35 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 0324 | 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
DeepSeek V3 0324 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 0324 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 0324 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 V3 0324 | SpaceXAI Grok 4.20 |
|---|---|---|
| Maker | DeepSeek | xAI |
| Weights | Open weights | No public weights listed |
| Released | March 24, 2025 | March 31, 2026 |
| Context window | 164K | 2M |
| Input $/Mtok | $0.27 | $1.25 |
| Output $/Mtok | $1.07 | $2.50 |
| Coding index | Not benchmarked | 33.3 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | $0.72 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 0324 better than Grok 4.20 for coding?
Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; DeepSeek V3 0324 has none, so the two cannot be ranked on coding. Pick DeepSeek V3 0324 for output tokens 2.3x cheaper ($1.07 vs $2.50 per million).
Which is cheaper, DeepSeek V3 0324 or Grok 4.20?
DeepSeek V3 0324 costs $0.27 per million input tokens and $1.07 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Cost per solved task is known for Grok 4.20 only.
Which has the bigger context window, DeepSeek V3 0324 or Grok 4.20?
Grok 4.20, with 2M tokens against 164K.
How many benchmarks is the DeepSeek V3 0324 vs Grok 4.20 comparison based on?
18 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3 0324's coding index rests on 0 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.