Command A vs Grok 4.20
Updated October 21, 2026. 23 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; Command A has none, so the two cannot be ranked on coding.
Command A has the edge where what matters is LegalBench (Vals AI) or CaseLaw (Vals AI), where it leads.
- Shared results
- 23
- Command A only
- 37
- Grok 4.20 only
- 31
- 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, 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 13.1.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Command A has a AA Agentic Index result, 1.0.
Directional only
Reasoning
GPQA Diamond
Grok 4.20
Grok 4.20 leads, 88.6% against 48.5%.
Same board, both measured
Math
AIME
Grok 4.20
Grok 4.20 leads, 96.5% against 13.3%.
Same board, both measured
Knowledge
MMLU Pro
Grok 4.20
Grok 4.20 leads, 86.3% against 69.2%.
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 256K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Grok 4.20
Command A $0.0075, Grok 4.20 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Grok 4.20
Command A $2.69, Grok 4.20 $0.72.
Published attempt cost and pass rate
At a glance
- Coding index
- Command A not benchmarked, Grok 4.20 33.3 from 2 benchmarks.
- Widest category
- Math, 83.1 points apart on average over 1 shared benchmark.
- Widest single gap
- AIME: Command A 13.3% against Grok 4.20 96.5%, 83.1 points apart on a 0 to 100 scale.
- Output price
- Command A $10.00 against Grok 4.20 $2.50 per million output tokens, 4.0x apart.
- Context window
- Command A takes 256K 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 | Command A | Bars | Grok 4.20 | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 1 | ||
| Knowledge | 2 | 5 | ||
| General | 0 | 5 | ||
| All shared boards | 2 | 21 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| AA Coding Index | 27.8 | Not measured | Only Command A measured |
| LiveCodeBench (Vals AI) | 35.1% | 84.3% | Grok 4.20 |
| SWE-bench Verified (Vals AI) | 7.8% | 72.2% | Grok 4.20 |
| 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) | 17.6% | 44.2% | Grok 4.20 |
| LiveCodeBench (Artificial Analysis run) | 28.7% | Not measured | Only Command A measured |
| SciCode | 38.5% | Not measured | Only Command A measured |
| Terminal-Bench Hard (Artificial Analysis run) | 25.0% | 37.9% | Grok 4.20 |
| Terminal-Bench | Not measured | 57.3% | Only Grok 4.20 measured |
| WeirdML | Not measured | 52.3% | Only Grok 4.20 measured |
| LMArena Text: coding | 1330 | Not measured | Only Command A measured |
| LMArena Text: software and IT | 1336 | Not measured | Only Command A measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.1 | 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 index02
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| AA Agentic Index | 1.0 | Not measured | Only Command A 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 | 1052 | 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) | 9.0% | 28.5% | Grok 4.20 |
| 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 | 80.7% | 93.0% | Grok 4.20 |
| Vending-Bench 2 | Not measured | $4,663 | Only Grok 4.20 measured |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| GPQA Diamond | 48.5% | 88.6% | Grok 4.20 |
| MMMU Pro (Vals AI) | Not measured | 83.5% | Only Grok 4.20 measured |
| GPQA Diamond (Artificial Analysis run) | 76.1% | 91.1% | Grok 4.20 |
| Humanity's Last Exam (Artificial Analysis run) | 12.0% | 34.5% | Grok 4.20 |
| ARC-AGI | Not measured | 89.5% | Only Grok 4.20 measured |
| ARC-AGI-2 | Not measured | 65.1% | Only Grok 4.20 measured |
| LMArena Text: hard prompts | 1326 | Not measured | Only Command A measured |
| LMArena Text: expert | 1296 | Not measured | Only Command A measured |
| LMArena Text: hard prompts in English | 1335 | Not measured | Only Command A measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| AIME | 13.3% | 96.5% | Grok 4.20 |
| MATH 500 (Vals AI) | 76.2% | Not measured | Only Command A measured |
| MGSM (Vals AI) | 85.7% | Not measured | Only Command A measured |
| AA Math Index | 13.0 | Not measured | Only Command A measured |
| AIME 2025 (Artificial Analysis run) | 13.0% | Not measured | Only Command A measured |
| LMArena Text: math | 1300 | Not measured | Only Command A measured |
| LMArena Text: mathematical work | 1312 | Not measured | Only Command A measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index25
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| MMLU Pro | 69.2% | 86.3% | Grok 4.20 |
| LegalBench (Vals AI) | 79.7% | 77.7% | Command A |
| CaseLaw (Vals AI) | 64.5% | 54.4% | Command A |
| CorpFin (Vals AI) | 46.0% | 63.7% | Grok 4.20 |
| TaxEval (Vals AI) | 61.4% | 74.1% | Grok 4.20 |
| MortgageTax (Vals AI) | Not measured | 45.4% | Only Grok 4.20 measured |
| MedQA (Vals AI) | 80.5% | 94.5% | Grok 4.20 |
| MedCode (Vals AI) | 19.7% | 32.2% | Grok 4.20 |
| MMLU Pro (Artificial Analysis run) | 71.2% | Not measured | Only Command A measured |
| LMArena Text: science | 1339 | Not measured | Only Command A measured |
| LMArena Text: medicine and healthcare | 1334 | Not measured | Only Command A measured |
| LMArena Text: legal and government | 1348 | Not measured | Only Command A measured |
| LMArena Text: business and finance | 1315 | Not measured | Only Command A measured |
| Neither model has a result on the other 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1229 | Only Grok 4.20 measured |
| Design Arena: UI components | Not measured | 1199 | Only Grok 4.20 measured |
| Design Arena: game dev | Not measured | 1192 | 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 | 1164 | Only Grok 4.20 measured |
| Design Arena: ASCII art | Not measured | 1174 | 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 index05
| Benchmark | Command A | Grok 4.20 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 38.2% | Only Grok 4.20 measured |
| MedScribe (Vals AI) | 55.7% | 63.4% | Grok 4.20 |
| Vals Multimodal Index | Not measured | 39.1% | Only Grok 4.20 measured |
| IFBench | 73.9% | 81.2% | Grok 4.20 |
| Long context reasoning (AA-LCR) | 52.7% | 69.0% | Grok 4.20 |
| DTBench | 61.3% | 90.1% | Grok 4.20 |
| LMCA | 10.3% | 38.7% | Grok 4.20 |
| CL-bench | Not measured | 22.2% | Only Grok 4.20 measured |
| CL-bench Life | Not measured | 11.9% | Only Grok 4.20 measured |
| LMArena Text | 1331 | Not measured | Only Command A measured |
| LMArena Text: instruction following | 1309 | Not measured | Only Command A measured |
| LMArena Text: creative writing | 1319 | Not measured | Only Command A measured |
| LMArena Text: English | 1344 | Not measured | Only Command A measured |
| LMArena Text: non-English | 1313 | Not measured | Only Command A measured |
| LMArena Text: Chinese | 1327 | Not measured | Only Command A measured |
| LMArena Text: German | 1342 | Not measured | Only Command A measured |
| LMArena Text: Japanese | 1285 | Not measured | Only Command A measured |
| LMArena Text: Korean | 1285 | Not measured | Only Command A measured |
| LMArena Text: French | 1351 | Not measured | Only Command A measured |
| LMArena Text: Spanish | 1347 | Not measured | Only Command A measured |
| LMArena Text: Russian | 1314 | Not measured | Only Command A measured |
| LMArena Text: Polish | 1324 | Not measured | Only Command A measured |
| LMArena Text: multi-turn | 1338 | Not measured | Only Command A measured |
| LMArena Text: longer queries | 1334 | Not measured | Only Command A measured |
| LMArena Text: writing and language | 1328 | Not measured | Only Command A measured |
| LMArena Text: entertainment and media | 1306 | Not measured | Only Command A measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Command A | 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 | Cohere Command A | SpaceXAI Grok 4.20 |
|---|---|---|
| Maker | Cohere | xAI |
| Weights | Open weights | No public weights listed |
| Released | March 13, 2025 | March 31, 2026 |
| Context window | 256K | 2M |
| Input $/Mtok | $2.50 | $1.25 |
| Output $/Mtok | $10.00 | $2.50 |
| Coding index | Not benchmarked | 33.3 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $2.69 | $0.72 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Command A better than Grok 4.20 for coding?
Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; Command A has none, so the two cannot be ranked on coding. Command A has the edge where what matters is LegalBench (Vals AI) or CaseLaw (Vals AI), where it leads.
Which is cheaper, Command A or Grok 4.20?
Command A costs $2.50 per million input tokens and $10.00 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Per solved SWE-bench Verified task, Command A costs $2.69 and Grok 4.20 $0.72.
Which has the bigger context window, Command A or Grok 4.20?
Grok 4.20, with 2M tokens against 256K.
How many benchmarks is the Command A vs Grok 4.20 comparison based on?
23 benchmarks have a result for both models as of October 21, 2026. Command A's coding index rests on 1 independent benchmark and Grok 4.20's on 2. Where only one model has a result, the page says so instead of naming a winner.