Model comparison
Grok 4.7 vs Llama 4 Scout
Grok 4.7 is the stronger model overall, scoring 53.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Grok 4.7 scores higher in 10 categories and Llama 4 Scout in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 9.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.1% for Grok 4.7 and 7.8% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Grok 4.7 | Llama 4 Scout | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 53.1 | 27.7 |
| Released | 2026-09-21 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 500K | 128K |
| Max output | 500K | 4K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $6 | $0.30 |
| Results tracked | 39 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Grok 4.7: 58.0 (#18), Llama 4 Scout: 20.2 (#339)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| SciCode | 57.8% | 17% |
| LMArena Coding | 1427 | 1286 |
| FrontierCode | 47.6% | — |
| SWE-bench Verified (bash only) | — | 9.1% |
| CursorBench | 46.3% | — |
| LMArena WebDev | 1639 | — |
| FrontierSWE | 29.5% | — |
| BigCodeBench Complete | — | 43.1% |
Agentic & Tool Use Grok 4.7 leads
Grok 4.7: 36.7 (#37), Llama 4 Scout: 24.6 (#119)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| APEX-Agents | 54.6% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| GDP.pdf | 22.8% | — |
| Vending-Bench 2 | 10,537 | — |
Reasoning Grok 4.7 leads
Grok 4.7: 49.1 (#40), Llama 4 Scout: 9.1 (#345)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| CritPt | 18% | 0% |
| LMArena Hard Prompts | 1413 | 1266 |
| DTBench | 96% | 57.9% |
| LMCA | 49.4% | 12% |
| Epoch Capabilities Index | 153.53 | 129.64 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| NYT Connections (extended) | 76.8% | — |
| ARC-AGI-1 | — | 0.5% |
| Chess Puzzles | 38% | — |
| Mystery Game Puzzles | 29% | — |
| ForecastBench | — | 57.5 |
Math Grok 4.7 leads
Grok 4.7: 57.8 (#39), Llama 4 Scout: 19.6 (#286)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.1% | 7.8% |
| LMArena Math | 1407 | 1287 |
| FrontierMath (Tiers 1-3) | 53% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 34% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Grok 4.7 leads
Grok 4.7: 62.8 (#22), Llama 4 Scout: 31.9 (#217)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 92.7% | 51.8% |
| LMArena Expert | 1422 | 1235 |
| SimpleQA Verified | 56% | — |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
Multimodal Grok 4.7 leads
Grok 4.7: 35.5 (#87), Llama 4 Scout: 32.2 (#102)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1228 | 1118 |
| Blueprint-Bench 2 | 32.5% | — |
| Furniture Assembly | 20.8% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Grok 4.7 leads
Grok 4.7: 50.8 (#116), Llama 4 Scout: 41.0 (#212)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1389 | 1252 |
| LMArena Chinese | 1455 | 1255 |
| LMArena French | 1455 | 1282 |
| LMArena Russian | 1397 | 1263 |
| LMArena Spanish | 1400 | 1278 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1207 |
Instruction Following Grok 4.7 leads
Grok 4.7: 74.1 (#105), Llama 4 Scout: 65.8 (#217)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1404 | 1248 |
| IFEval | — | 81.8% |
Long Context Grok 4.7 leads
Grok 4.7: 43.1 (#104), Llama 4 Scout: 27.5 (#294)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1413 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Grok 4.7 leads
Grok 4.7: 70.0 (#24), Llama 4 Scout: 37.0 (#261)
| Benchmark | Grok 4.7 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1399 | 1279 |
| LMArena Creative Writing | 1391 | 1249 |
| EQ-Bench Creative Writing | 2007 | 783 |
| LMArena Multi-Turn | 1393 | 1280 |
| WildBench | — | 78% |
Frequently asked questions
Is Grok 4.7 better than Llama 4 Scout?
Grok 4.7 is the stronger model overall, scoring 53.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 20× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, Grok 4.7 or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Grok 4.7 lists at $2 and $6.
Is Grok 4.7 or Llama 4 Scout better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Grok 4.7 does, with 500K tokens against 128K.
How many benchmarks do Grok 4.7 and Llama 4 Scout share?
23 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Llama 4 Scout has 43.