Model comparison
Grok 4 vs Llama 4 Maverick
Grok 4 is the stronger model overall, scoring 48.1 to 30.9 on the Noometry Index.
Last verified . 39 shared benchmarks.
MetaSummary
- They share 39 benchmarks with published results for both. Grok 4 scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 31.4.
- The biggest single-benchmark swing is Aider Polyglot: 79.6% for Grok 4 and 15.6% for Llama 4 Maverick.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Grok 4 | Llama 4 Maverick | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.1 | 30.9 |
| Released | 2025-07-09 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 48 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Grok 4: 50.3 (#46), Llama 4 Maverick: 26.6 (#324)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| Aider Polyglot | 79.6% | 15.6% |
| WeirdML | 45.7% | 24.5% |
| LMArena Coding | 1408 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| SciCode | — | 33.1% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Grok 4 leads
Grok 4: 32.3 (#68), Llama 4 Maverick: 28.2 (#91)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | 37.3% |
| Terminal-Bench | 27.2% | — |
| GDPval | 21.1% | — |
| Cybench | 43% | — |
| DeepResearch Bench | 47.3% | — |
| BALROG | 43.6% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 66.6% | — |
Reasoning Grok 4 leads
Grok 4: 36.7 (#65), Llama 4 Maverick: 10.1 (#342)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 16% | 0% |
| SimpleBench | 60.5% | 27.7% |
| Kagi LLM Benchmark | 73.6% | 55.9% |
| ARC-AGI-1 | 66.7% | 4.4% |
| LMArena Hard Prompts | 1409 | 1281 |
| Epoch Capabilities Index | 146.44 | 132.2 |
| ForecastBench | 60.9 | 57.5 |
| NYT Connections (extended) | — | 8% |
| CritPt | — | 0% |
| Chess Puzzles | 28% | — |
| EnigmaEval | — | 0.6% |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
Math Grok 4 leads
Grok 4: 48.4 (#64), Llama 4 Maverick: 26.0 (#262)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84% | 20.6% |
| Omni-MATH | 60.3% | 42.2% |
| LMArena Math | 1422 | 1299 |
| FrontierMath (Feb 2025 set) | 19.7% | 0.7% |
| MATH Level 5 | — | 73% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Grok 4 leads
Grok 4: 53.8 (#55), Llama 4 Maverick: 33.4 (#204)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 87% | 67% |
| MMLU-Pro | 85.1% | 81% |
| Confabulations | 12.4% | 22.6% |
| GPQA (HELM) | 72.7% | 65% |
| LMArena Expert | 1415 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| Vectara Hallucination Rate | — | 8.2% |
Multimodal Grok 4 leads
Grok 4: 33.7 (#94), Llama 4 Maverick: 31.6 (#105)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1210 | 1142 |
| GeoBench | 45% | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Grok 4 leads
Grok 4: 51.8 (#103), Llama 4 Maverick: 42.2 (#195)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1403 | 1269 |
| LMArena Chinese | 1427 | 1277 |
| LMArena French | 1418 | 1259 |
| LMArena German | 1429 | 1291 |
| LMArena Japanese | 1394 | 1207 |
| LMArena Korean | 1377 | 1203 |
| LMArena Russian | 1410 | 1286 |
| LMArena Spanish | 1420 | 1293 |
Instruction Following Grok 4 leads
Grok 4: 79.2 (#5), Llama 4 Maverick: 71.7 (#146)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| IFEval | 94.9% | 90.8% |
| LMArena Instruction Following | 1387 | 1267 |
Long Context Grok 4 leads
Grok 4: 63.1 (#4), Llama 4 Maverick: 31.4 (#279)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | 94.4% | 46.2% |
| LMArena Longer Query | 1409 | 1280 |
Writing & Preference Grok 4 leads
Grok 4: 58.5 (#116), Llama 4 Maverick: 38.8 (#252)
| Benchmark | Grok 4 | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1411 | 1287 |
| LMArena Creative Writing | 1397 | 1267 |
| Short-Story Creative Writing | 76.9% | 62% |
| WildBench | 79.7% | 80% |
| LMArena Multi-Turn | 1416 | 1289 |
| EQ-Bench Creative Writing | — | 860 |
Frequently asked questions
Is Grok 4 better than Llama 4 Maverick?
Grok 4 is the stronger model overall, scoring 48.1 to 30.9 on the Noometry Index.
Is Grok 4 or Llama 4 Maverick better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 26.6 in the Noometry coding category.
How many benchmarks do Grok 4 and Llama 4 Maverick share?
39 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Llama 4 Maverick has 54.