Model comparison
GPT-5.2 vs Llama 4 Scout
GPT-5.2 is the stronger model overall, scoring 54.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 32× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. GPT-5.2 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 GPT-5.2 leads 50.2 to 9.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 96.1% for GPT-5.2 and 7.8% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- GPT-5.2 accepts more context: 400K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 | Llama 4 Scout | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 54.1 | 27.7 |
| Released | 2025-12-11 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $1.75 | $0.10 |
| Output $ / M tokens | $14 | $0.30 |
| Results tracked | 67 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
GPT-5.2: 51.6 (#37), Llama 4 Scout: 20.2 (#339)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | 9.1% |
| LMArena Coding | 1447 | 1286 |
| SWE-bench Verified | 73.8% | — |
| LMArena WebDev | 1416 | — |
| SWE-bench Multilingual | 66.7% | — |
| SciCode | — | 17% |
| GSO | 27.4% | — |
| WeirdML | 72.2% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 1,294 | — |
| AlgoTune | 2.05 | — |
Agentic & Tool Use GPT-5.2 leads
GPT-5.2: 40.2 (#24), Llama 4 Scout: 24.6 (#119)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 55.9% | 28.1% |
| Terminal-Bench | 64.9% | — |
| GDPval | 49.7% | — |
| Remote Labor Index | 2.5% | — |
| τ²-bench Airline | 83% | — |
| τ²-bench Banking | 32.2% | — |
| τ²-bench Retail | 81.6% | — |
| τ²-bench Telecom | 89.7% | — |
| DeepResearch Bench | 41.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 75.3% | — |
| Vending-Bench 2 | 3,591 | — |
Reasoning GPT-5.2 leads
GPT-5.2: 50.2 (#35), Llama 4 Scout: 9.1 (#345)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 52.9% | 0% |
| Kagi LLM Benchmark | 73.3% | 36.9% |
| ARC-AGI-1 | 86.2% | 0.5% |
| LMArena Hard Prompts | 1445 | 1266 |
| DTBench | 90.9% | 57.9% |
| LMCA | 43.9% | 12% |
| Epoch Capabilities Index | 153.45 | 129.64 |
| ForecastBench | 60.1 | 57.5 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 83.6% | — |
| CritPt | — | 0% |
| Chess Puzzles | 49% | — |
| EnigmaEval | 10.4% | — |
| EBR-Bench | 23% | — |
| Mystery Game Puzzles | 23% | — |
Math GPT-5.2 leads
GPT-5.2: 60.0 (#38), Llama 4 Scout: 19.6 (#286)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 96.1% | 7.8% |
| LMArena Math | 1440 | 1287 |
| FrontierMath (Feb 2025 set) | 40.7% | 0% |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 31.7% | — |
| MathArena Final-Answer Competitions | 72% | — |
| ProofBench | 15% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge GPT-5.2 leads
GPT-5.2: 59.3 (#32), Llama 4 Scout: 31.9 (#217)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 91.4% | 51.8% |
| Vectara Hallucination Rate | 8.4% | 7.7% |
| LMArena Expert | 1445 | 1235 |
| Humanity's Last Exam | 27.8% | — |
| SimpleQA Verified | 37.1% | — |
| MMLU-Pro | — | 74.2% |
| GPQA (HELM) | — | 50.7% |
Multimodal GPT-5.2 leads
GPT-5.2: 51.3 (#7), Llama 4 Scout: 32.2 (#102)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1268 | 1118 |
| VPCT | 84% | — |
| Furniture Assembly | 38.3% | — |
| LMArena Document | 1405 | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual GPT-5.2 leads
GPT-5.2: 53.4 (#67), Llama 4 Scout: 41.0 (#212)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1425 | 1252 |
| LMArena Chinese | 1460 | 1255 |
| LMArena French | 1455 | 1282 |
| LMArena German | 1448 | 1272 |
| LMArena Japanese | 1420 | 1206 |
| LMArena Korean | 1392 | 1207 |
| LMArena Russian | 1440 | 1263 |
| LMArena Spanish | 1433 | 1278 |
Instruction Following GPT-5.2 leads
GPT-5.2: 74.7 (#89), Llama 4 Scout: 65.8 (#217)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1417 | 1248 |
| IFEval | — | 81.8% |
Long Context GPT-5.2 leads
GPT-5.2: 44.0 (#78), Llama 4 Scout: 27.5 (#294)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1428 | 1265 |
| Fiction.LiveBench | — | 36% |
| CL-bench | 18.2% | — |
Writing & Preference GPT-5.2 leads
GPT-5.2: 66.8 (#32), Llama 4 Scout: 37.0 (#261)
| Benchmark | GPT-5.2 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1439 | 1279 |
| LMArena Creative Writing | 1401 | 1249 |
| EQ-Bench Creative Writing | 1703 | 783 |
| LMArena Multi-Turn | 1458 | 1280 |
| WildBench | — | 78% |
Frequently asked questions
Is GPT-5.2 better than Llama 4 Scout?
GPT-5.2 is the stronger model overall, scoring 54.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 32× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 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; GPT-5.2 lists at $1.75 and $14.
Is GPT-5.2 or Llama 4 Scout better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 does, with 400K tokens against 128K.
How many benchmarks do GPT-5.2 and Llama 4 Scout share?
32 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and Llama 4 Scout has 43.