Grok 4.20 vs Qwen3 30B A3B
Grok 4.20 leads Qwen3 30B A3B on the Artificial Analysis Intelligence Index, 25.7 to 7.6, and Qwen3 30B A3B costs 5.0x less per output token ($0.50 vs $2.50 per million). Updated October 22, 2026; 16 benchmarks have a result for both.
Grok 4.20 or Qwen3 30B A3B: which to pick
Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; Qwen3 30B A3B has none, so the two cannot be ranked on coding.
Pick Qwen3 30B A3B for output tokens 5.0x cheaper ($0.50 vs $2.50 per million).
- Shared results
- 16
- Grok 4.20 only
- 39
- Qwen3 30B A3B only
- 36
- Like-for-like categories
- 6 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 7.6.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Grok 4.20 has a GPQA Diamond result, 88.6%.
Directional only
Math
AIME
No call
Only Grok 4.20 has a AIME result, 96.5%.
Directional only
Knowledge
MMLU Pro
No call
Only Grok 4.20 has a MMLU Pro result, 86.3%.
Directional only
Web design
Design Arena: websites
Grok 4.20
Grok 4.20 leads, 1229 against 954.
Same board, both measured
Long documents
Listed context window
Grok 4.20
Grok 4.20 takes 2M tokens against 41K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 30B A3B
Grok 4.20 $0.0025, Qwen3 30B A3B $0.0004 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
- Grok 4.20 33.3 from 2 benchmarks, Qwen3 30B A3B not benchmarked.
- Widest category
- Agentic work, 67.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Grok 4.20 69.0% against Qwen3 30B A3B 0.0%, 69.0 points apart on a 0 to 100 scale.
- Output price
- Grok 4.20 $2.50 against Qwen3 30B A3B $0.50 per million output tokens, 5.0x apart.
- Context window
- Grok 4.20 takes 2M tokens, Qwen3 30B A3B 41K.
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 | Grok 4.20 | Bars | Qwen3 30B A3B | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| Web design | 5 | 0 | ||
| General | 4 | 0 | ||
| All shared boards | 16 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| LiveCodeBench (Vals AI) | 84.3% | Not measured | Only Grok 4.20 measured |
| SWE-bench Verified (Vals AI) | 72.2% | Not measured | Only Grok 4.20 measured |
| Vibe Code Bench (Vals AI) | 4.1% | Not measured | Only Grok 4.20 measured |
| Code migration (Vals AI) | 0.3% | Not measured | Only Grok 4.20 measured |
| Terminal-Bench 2.1 (Vals AI) | 44.2% | Not measured | Only Grok 4.20 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 50.6% | Only Qwen3 30B A3B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 37.9% | 6.8% | Grok 4.20 |
| Terminal-Bench | 57.3% | Not measured | Only Grok 4.20 measured |
| WeirdML | 52.3% | 29.8% | Grok 4.20 |
| LMArena Text: coding | Not measured | 1337 | Only Qwen3 30B A3B measured |
| LMArena Text: software and IT | Not measured | 1340 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AA Intelligence Index | 25.7 | 7.6 | Grok 4.20 |
| Epoch Capabilities Index | 152.1 | 137.3 | Grok 4.20 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1144 | Not measured | Only Grok 4.20 measured |
| Design Arena: agents building full-stack apps | 1054 | Not measured | Only Grok 4.20 measured |
| Design Arena: agents building mobile apps | 1090 | Not measured | Only Grok 4.20 measured |
| Design Arena: agents building Android apps | 1045 | Not measured | Only Grok 4.20 measured |
| Design Arena: agents building Godot games | 1089 | Not measured | Only Grok 4.20 measured |
| Design Arena: HTML slides | 1180 | Not measured | Only Grok 4.20 measured |
| Finance Agent (Vals AI) | 28.5% | Not measured | Only Grok 4.20 measured |
| Tax Agent Bench (Vals AI) | 7.0% | Not measured | Only Grok 4.20 measured |
| Legal Research Bench (Vals AI) | 13.9% | Not measured | Only Grok 4.20 measured |
| Excel Modeling Benchmark (Vals AI) | 11.7% | Not measured | Only Grok 4.20 measured |
| τ²-Bench Telecom | 93.0% | 26.0% | Grok 4.20 |
| Vending-Bench 2 | $4,663 | Not measured | Only Grok 4.20 measured |
| Neither model has a result on the other 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| GPQA Diamond | 88.6% | Not measured | Only Grok 4.20 measured |
| MMMU Pro (Vals AI) | 83.5% | Not measured | Only Grok 4.20 measured |
| GPQA Diamond (Artificial Analysis run) | 91.1% | 61.6% | Grok 4.20 |
| Humanity's Last Exam (Artificial Analysis run) | 34.5% | 6.2% | Grok 4.20 |
| GPQA Diamond (Epoch AI run) | Not measured | 61.7% | Only Qwen3 30B A3B measured |
| ARC-AGI | 89.5% | Not measured | Only Grok 4.20 measured |
| ARC-AGI-2 | 65.1% | Not measured | Only Grok 4.20 measured |
| LMArena Text: hard prompts | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: expert | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: hard prompts in English | Not measured | 1329 | Only Qwen3 30B A3B measured |
| Kagi LLM Benchmark | 75.0% | Not measured | Only Grok 4.20 measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AIME | 96.5% | Not measured | Only Grok 4.20 measured |
| AA Math Index | Not measured | 72.3 | Only Qwen3 30B A3B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 72.3% | Only Qwen3 30B A3B measured |
| OTIS Mock AIME | Not measured | 62.8% | Only Qwen3 30B A3B measured |
| LMArena Text: math | Not measured | 1355 | Only Qwen3 30B A3B measured |
| LMArena Text: mathematical work | Not measured | 1363 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| MMLU Pro | 86.3% | Not measured | Only Grok 4.20 measured |
| LegalBench (Vals AI) | 77.7% | Not measured | Only Grok 4.20 measured |
| CaseLaw (Vals AI) | 54.4% | Not measured | Only Grok 4.20 measured |
| CorpFin (Vals AI) | 63.7% | Not measured | Only Grok 4.20 measured |
| TaxEval (Vals AI) | 74.1% | Not measured | Only Grok 4.20 measured |
| MortgageTax (Vals AI) | 45.4% | Not measured | Only Grok 4.20 measured |
| MedQA (Vals AI) | 94.5% | Not measured | Only Grok 4.20 measured |
| MedCode (Vals AI) | 32.2% | Not measured | Only Grok 4.20 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 77.7% | Only Qwen3 30B A3B measured |
| LMArena Text: science | Not measured | 1321 | Only Qwen3 30B A3B measured |
| LMArena Text: medicine and healthcare | Not measured | 1318 | Only Qwen3 30B A3B measured |
| LMArena Text: legal and government | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: business and finance | Not measured | 1309 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| Design Arena: websites | 1229 | 954 | Grok 4.20 |
| Design Arena: UI components | 1200 | 943 | Grok 4.20 |
| Design Arena: game dev | 1193 | 898 | Grok 4.20 |
| Design Arena: data viz | 1217 | 967 | Grok 4.20 |
| Design Arena: 3D | 1193 | Not measured | Only Grok 4.20 measured |
| Design Arena: all code categories | 1221 | 941 | Grok 4.20 |
| Design Arena: SVG | 1165 | Not measured | Only Grok 4.20 measured |
| Design Arena: ASCII art | 1175 | Not measured | 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 index40
| Benchmark | Grok 4.20 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 38.2% | Not measured | Only Grok 4.20 measured |
| MedScribe (Vals AI) | 63.4% | Not measured | Only Grok 4.20 measured |
| Vals Multimodal Index | 39.1% | Not measured | Only Grok 4.20 measured |
| IFBench | 81.2% | 41.5% | Grok 4.20 |
| Long context reasoning (AA-LCR) | 69.0% | 0.0% | Grok 4.20 |
| DTBench | 90.1% | 60.3% | Grok 4.20 |
| LMCA | 38.7% | 15.8% | Grok 4.20 |
| Fiction.LiveBench | Not measured | 40.6% | Only Qwen3 30B A3B measured |
| Creative writing (Lech Mazur) | Not measured | 75.3% | Only Qwen3 30B A3B measured |
| CL-bench | 22.2% | Not measured | Only Grok 4.20 measured |
| CL-bench Life | 11.9% | Not measured | Only Grok 4.20 measured |
| LMArena Text | Not measured | 1317 | Only Qwen3 30B A3B measured |
| LMArena Text: instruction following | Not measured | 1283 | Only Qwen3 30B A3B measured |
| LMArena Text: creative writing | Not measured | 1271 | Only Qwen3 30B A3B measured |
| LMArena Text: English | Not measured | 1335 | Only Qwen3 30B A3B measured |
| LMArena Text: non-English | Not measured | 1295 | Only Qwen3 30B A3B measured |
| LMArena Text: Chinese | Not measured | 1347 | Only Qwen3 30B A3B measured |
| LMArena Text: German | Not measured | 1307 | Only Qwen3 30B A3B measured |
| LMArena Text: Japanese | Not measured | 1254 | Only Qwen3 30B A3B measured |
| LMArena Text: Korean | Not measured | 1261 | Only Qwen3 30B A3B measured |
| LMArena Text: French | Not measured | 1352 | Only Qwen3 30B A3B measured |
| LMArena Text: Spanish | Not measured | 1317 | Only Qwen3 30B A3B measured |
| LMArena Text: Russian | Not measured | 1291 | Only Qwen3 30B A3B measured |
| LMArena Text: Polish | Not measured | 1299 | Only Qwen3 30B A3B measured |
| LMArena Text: multi-turn | Not measured | 1307 | Only Qwen3 30B A3B measured |
| LMArena Text: longer queries | Not measured | 1312 | Only Qwen3 30B A3B measured |
| LMArena Text: writing and language | Not measured | 1290 | Only Qwen3 30B A3B measured |
| LMArena Text: entertainment and media | Not measured | 1258 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Grok 4.20 | Qwen3 30B A3B | 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
Qwen3 30B A3B costs less
Repository review
50K input + 3K output tokens
Qwen3 30B A3B costs less
Agent loop
200K input + 10K output tokens
Qwen3 30B A3B 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 | SpaceXAI Grok 4.20 | Qwen3 30B A3B |
|---|---|---|
| Maker | xAI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | March 31, 2026 | April 28, 2025 |
| Context window | 2M | 41K |
| Input $/Mtok | $1.25 | $0.12 |
| Output $/Mtok | $2.50 | $0.50 |
| Coding index | 33.3 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | $0.72 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Grok 4.20 better than Qwen3 30B A3B for coding?
Only Grok 4.20 has a coding score, 33.3 on the Vibe Coding Index; Qwen3 30B A3B has none, so the two cannot be ranked on coding. Pick Qwen3 30B A3B for output tokens 5.0x cheaper ($0.50 vs $2.50 per million).
Which is cheaper, Grok 4.20 or Qwen3 30B A3B?
Grok 4.20 costs $1.25 per million input tokens and $2.50 per million output tokens; Qwen3 30B A3B costs $0.12 and $0.50. Cost per solved task is known for Grok 4.20 only.
Which has the bigger context window, Grok 4.20 or Qwen3 30B A3B?
Grok 4.20, with 2M tokens against 41K.
How many benchmarks is the Grok 4.20 vs Qwen3 30B A3B comparison based on?
16 benchmarks have a result for both models as of October 22, 2026. Grok 4.20's coding index rests on 2 independent benchmarks and Qwen3 30B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.