Model comparison
GPT-5.2 Pro vs Llama 4 Maverick
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 190× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
MetaSummary
- They share 5 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and Llama 4 Maverick in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.5 to 10.1.
- The biggest single-benchmark swing is ARC-AGI-1: 90.5% for GPT-5.2 Pro and 4.4% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 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 Maverick has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Llama 4 Maverick | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 52.3 | 30.9 |
| Released | 2025-12-11 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $21 | $0.19 |
| Output $ / M tokens | $168 | $0.65 |
| Results tracked | 8 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 26.6 (#324)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| LMArena Coding | — | 1302 |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 28.2 (#91)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Llama 4 Maverick: 10.1 (#342)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 54.2% | 0% |
| SimpleBench | 57.4% | 27.7% |
| NYT Connections (extended) | 79.3% | 8% |
| ARC-AGI-1 | 90.5% | 4.4% |
| Epoch Capabilities Index | 155.4 | 132.2 |
| Kagi LLM Benchmark | — | 55.9% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| LMArena Hard Prompts | — | 1281 |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| ForecastBench | — | 57.5 |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Llama 4 Maverick: 26.0 (#262)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| Omni-MATH | — | 42.2% |
| LMArena Math | — | 1299 |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 33.4 (#204)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
| LMArena Expert | — | 1259 |
Multimodal Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 31.6 (#105)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 42.2 (#195)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1277 |
| LMArena French | — | 1259 |
| LMArena German | — | 1291 |
| LMArena Japanese | — | 1207 |
| LMArena Korean | — | 1203 |
| LMArena Russian | — | 1286 |
| LMArena Spanish | — | 1293 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 71.7 (#146)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| IFEval | — | 90.8% |
| LMArena Instruction Following | — | 1267 |
Long Context Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 31.4 (#279)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | — | 46.2% |
| LMArena Longer Query | — | 1280 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Llama 4 Maverick: 38.8 (#252)
| Benchmark | GPT-5.2 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Text | — | 1287 |
| LMArena Creative Writing | — | 1267 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
| LMArena Multi-Turn | — | 1289 |
Frequently asked questions
Is GPT-5.2 Pro better than Llama 4 Maverick?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 190× 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 Maverick?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 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 Maverick share?
5 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Llama 4 Maverick has 54.