Model comparison
Claude Opus 4 vs Llama 4 Scout
Claude Opus 4 is the stronger model overall, scoring 43.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 200× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 39 shared benchmarks.
MetaSummary
- They share 39 benchmarks with published results for both. Claude Opus 4 scores higher in 9 categories and Llama 4 Scout in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.2 to 20.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 67.6% for Claude Opus 4 and 9.1% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Claude Opus 4 accepts more context: 200K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | Llama 4 Scout | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 43.1 | 27.7 |
| Released | 2025-05-22 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 200K | 128K |
| Max output | 32K | 4K |
| Input $ / M tokens | $15 | $0.10 |
| Output $ / M tokens | $75 | $0.30 |
| Results tracked | 56 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), Llama 4 Scout: 20.2 (#339)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | 67.6% | 9.1% |
| LMArena Coding | 1442 | 1286 |
| SWE-bench Verified | 70.7% | — |
| Aider Polyglot | 72% | — |
| SciCode | — | 17% |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| BigCodeBench Complete | — | 43.1% |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Llama 4 Scout: 24.6 (#119)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), Llama 4 Scout: 9.1 (#345)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 8.6% | 0% |
| Kagi LLM Benchmark | 74.3% | 36.9% |
| ARC-AGI-1 | 35.7% | 0.5% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1399 | 1266 |
| DTBench | 81.6% | 57.9% |
| LMCA | 37.4% | 12% |
| Epoch Capabilities Index | 142.67 | 129.64 |
| ForecastBench | 61.1 | 57.5 |
| SimpleBench | 58.8% | — |
| EnigmaEval | 5.6% | — |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Llama 4 Scout: 19.6 (#286)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 7.8% |
| Omni-MATH | 61.6% | 37.3% |
| LMArena Math | 1390 | 1287 |
| MATH Level 5 | 85% | 62.3% |
| FrontierMath (Feb 2025 set) | 4.5% | 0% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), Llama 4 Scout: 31.9 (#217)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 76.3% | 51.8% |
| MMLU-Pro | 87.5% | 74.2% |
| Vectara Hallucination Rate | 12% | 7.7% |
| GPQA (HELM) | 70.8% | 50.7% |
| LMArena Expert | 1386 | 1235 |
| Humanity's Last Exam | 10.7% | — |
| Confabulations | 15.9% | — |
Multimodal Too close to call
Claude Opus 4: 31.5 (#106), Llama 4 Scout: 32.2 (#102)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1192 | 1118 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Claude Opus 4 leads
Claude Opus 4: 48.8 (#138), Llama 4 Scout: 41.0 (#212)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1362 | 1252 |
| LMArena Chinese | 1386 | 1255 |
| LMArena French | 1372 | 1282 |
| LMArena German | 1391 | 1272 |
| LMArena Japanese | 1331 | 1206 |
| LMArena Korean | 1321 | 1207 |
| LMArena Russian | 1392 | 1263 |
| LMArena Spanish | 1389 | 1278 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Llama 4 Scout: 65.8 (#217)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| IFEval | 91.8% | 81.8% |
| LMArena Instruction Following | 1406 | 1248 |
Long Context Claude Opus 4 leads
Claude Opus 4: 39.6 (#172), Llama 4 Scout: 27.5 (#294)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | 61.1% | 36% |
| LMArena Longer Query | 1422 | 1265 |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), Llama 4 Scout: 37.0 (#261)
| Benchmark | Claude Opus 4 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1377 | 1279 |
| LMArena Creative Writing | 1387 | 1249 |
| EQ-Bench Creative Writing | 1580 | 783 |
| WildBench | 85.2% | 78% |
| LMArena Multi-Turn | 1396 | 1280 |
| Short-Story Creative Writing | 83.6% | — |
Frequently asked questions
Is Claude Opus 4 better than Llama 4 Scout?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 200× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 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; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Llama 4 Scout better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4 does, with 200K tokens against 128K.
How many benchmarks do Claude Opus 4 and Llama 4 Scout share?
39 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Llama 4 Scout has 43.