Model comparison
GPT-5.2 Pro vs Llama 4 Scout
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 27.7 on the Noometry Index. Llama 4 Scout costs 385× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
MetaSummary
- They share 3 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and Llama 4 Scout in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 19.6.
- The biggest single-benchmark swing is ARC-AGI-1: 90.5% for GPT-5.2 Pro and 0.5% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro 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 Pro | Llama 4 Scout | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 52.3 | 27.7 |
| Released | 2025-12-11 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $21 | $0.10 |
| Output $ / M tokens | $168 | $0.30 |
| Results tracked | 8 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 20.2 (#339)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| LMArena Coding | — | 1286 |
| BigCodeBench Complete | — | 43.1% |
Agentic & Tool Use Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 24.6 (#119)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Llama 4 Scout: 9.1 (#345)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 54.2% | 0% |
| ARC-AGI-1 | 90.5% | 0.5% |
| Epoch Capabilities Index | 155.4 | 129.64 |
| SimpleBench | 57.4% | — |
| Kagi LLM Benchmark | — | 36.9% |
| NYT Connections (extended) | 79.3% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1266 |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| ForecastBench | — | 57.5 |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Llama 4 Scout: 19.6 (#286)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| Omni-MATH | — | 37.3% |
| LMArena Math | — | 1287 |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 31.9 (#217)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | — | 51.8% |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1235 |
Multimodal Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 41.0 (#212)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1255 |
| LMArena French | — | 1282 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1207 |
| LMArena Russian | — | 1263 |
| LMArena Spanish | — | 1278 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 65.8 (#217)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| IFEval | — | 81.8% |
| LMArena Instruction Following | — | 1248 |
Long Context Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 27.5 (#294)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | — | 36% |
| LMArena Longer Query | — | 1265 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Llama 4 Scout: 37.0 (#261)
| Benchmark | GPT-5.2 Pro | Llama 4 Scout |
|---|---|---|
| LMArena Text | — | 1279 |
| LMArena Creative Writing | — | 1249 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
| LMArena Multi-Turn | — | 1280 |
Frequently asked questions
Is GPT-5.2 Pro better than Llama 4 Scout?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 27.7 on the Noometry Index. Llama 4 Scout costs 385× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 Pro 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 Pro lists at $21 and $168.
Which has the bigger context window?
GPT-5.2 Pro does, with 400K tokens against 128K.
How many benchmarks do GPT-5.2 Pro and Llama 4 Scout share?
3 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Llama 4 Scout has 43.