Model comparison
Grok 4.3 vs Llama 4 Maverick
Grok 4.3 is the stronger model overall, scoring 43.6 to 30.6 on the Noometry Index. Llama 4 Maverick costs 5.1× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Grok 4.3 scores higher in 9 categories and Llama 4 Maverick in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 34.9 to 10.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Grok 4.3 and 20.6% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Grok 4.3 accepts more context: 1M tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Grok 4.3 | Llama 4 Maverick | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 43.6 | 30.6 |
| Released | 2026-04-17 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 1M | 128K |
| Max output | 30K | 4K |
| Input $ / M tokens | $1.25 | $0.19 |
| Output $ / M tokens | $2.50 | $0.65 |
| Results tracked | 40 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
Grok 4.3: 41.3 (#117), Llama 4 Maverick: 26.3 (#318)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| SciCode | 47.3% | 33.1% |
| WeirdML | 49.9% | 24.5% |
| LMArena Coding | 1415 | 1302 |
| ALE-Bench | 944.17 | 172.97 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1357 | — |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
Agentic & Tool Use Too close to call
Grok 4.3: 27.6 (#93), Llama 4 Maverick: 27.9 (#86)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |
Reasoning Grok 4.3 leads
Grok 4.3: 34.9 (#60), Llama 4 Maverick: 10.1 (#337)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| NYT Connections (extended) | 55.2% | 8% |
| CritPt | 8% | 0% |
| LMArena Hard Prompts | 1397 | 1281 |
| DTBench | 90.7% | 61.9% |
| LMCA | 38.3% | 15.9% |
| Epoch Capabilities Index | 149.13 | 132.2 |
| ForecastBench | 60.3 | 57.5 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| ARC-AGI-1 | — | 4.4% |
| Chess Puzzles | 25% | — |
| EnigmaEval | — | 0.6% |
Math Grok 4.3 leads
Grok 4.3: 45.8 (#60), Llama 4 Maverick: 24.6 (#256)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 20.6% |
| LMArena Math | 1388 | 1299 |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| ProofBench | 11% | — |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Grok 4.3 leads
Grok 4.3: 52.5 (#57), Llama 4 Maverick: 33.3 (#196)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 88.8% | 67% |
| LMArena Expert | 1385 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| SimpleQA Verified | 33.2% | — |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
Multimodal Too close to call
Grok 4.3: 31.6 (#96), Llama 4 Maverick: 30.9 (#100)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1231 | 1141 |
| GeoBench | — | 52% |
| Blueprint-Bench 2 | 0% | — |
| SpatialViz-Bench | — | 31.8% |
Multilingual Grok 4.3 leads
Grok 4.3: 50.7 (#114), Llama 4 Maverick: 42.4 (#190)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1385 | 1269 |
| LMArena Chinese | 1423 | 1277 |
| LMArena French | 1412 | 1258 |
| LMArena German | 1395 | 1291 |
| LMArena Japanese | 1379 | 1207 |
| LMArena Korean | 1357 | 1203 |
| LMArena Russian | 1399 | 1286 |
| LMArena Spanish | 1402 | 1293 |
Instruction Following Too close to call
Grok 4.3: 72.3 (#135), Llama 4 Maverick: 71.9 (#140)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1366 | 1267 |
| IFEval | — | 90.8% |
Long Context Grok 4.3 leads
Grok 4.3: 42.5 (#118), Llama 4 Maverick: 31.4 (#274)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1393 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Grok 4.3 leads
Grok 4.3: 58.6 (#112), Llama 4 Maverick: 39.0 (#247)
| Benchmark | Grok 4.3 | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1397 | 1287 |
| LMArena Creative Writing | 1380 | 1266 |
| LMArena Multi-Turn | 1406 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
| EQ-Bench 4 | 1075 | — |
Frequently asked questions
Is Grok 4.3 better than Llama 4 Maverick?
Grok 4.3 is the stronger model overall, scoring 43.6 to 30.6 on the Noometry Index. Llama 4 Maverick costs 5.1× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Which is cheaper, Grok 4.3 or Llama 4 Maverick?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is Grok 4.3 or Llama 4 Maverick better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.3 versus 26.3 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 128K.
How many benchmarks do Grok 4.3 and Llama 4 Maverick share?
29 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Llama 4 Maverick has 54.