Model comparison
GPT-4.1 vs Llama 3.2 90B
GPT-4.1 is the stronger model overall, scoring 35.7 to 27.1 on the Noometry Index.
Last verified . 7 shared benchmarks.
MetaSummary
- They share 7 benchmarks with published results for both. GPT-4.1 scores higher in 4 categories and Llama 3.2 90B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 leads 37.0 to 21.7.
- The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 39.4% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Llama 3.2 90B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 35.7 | 27.1 |
| Released | 2025-04-14 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-4.1: 34.2 (#228), Llama 3.2 90B: —
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| LMArena Coding | 1391 | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.4 (#40), Llama 3.2 90B: 29.7 (#73)
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| BALROG | — | 27.3% |
Reasoning Llama 3.2 90B leads
GPT-4.1: 11.7 (#334), Llama 3.2 90B: 20.9 (#207)
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | 2.2% | 0.4% |
| Epoch Capabilities Index | 136.79 | 125.5 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1384 | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| ForecastBench | 61.5 | — |
Math GPT-4.1 leads
GPT-4.1: 21.4 (#269), Llama 3.2 90B: 10.4 (#302)
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 2.6% |
| MATH Level 5 | 83% | 39.4% |
| FrontierMath (Tiers 1-3) | 6% | — |
| Omni-MATH | 47.1% | — |
| LMArena Math | 1369 | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.0 (#152), Llama 3.2 90B: 21.7 (#269)
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 66.9% | 41% |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
| LMArena Expert | 1364 | — |
| MMLU | — | 80.3% |
Multimodal GPT-4.1 leads
GPT-4.1: 37.5 (#66), Llama 3.2 90B: 24.9 (#119)
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | 1210 | 1000 |
| GeoBench | 72% | 52% |
Multilingual Not comparable
GPT-4.1: 49.6 (#128), Llama 3.2 90B: —
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1370 | — |
| LMArena Chinese | 1382 | — |
| LMArena French | 1383 | — |
| LMArena German | 1380 | — |
| LMArena Japanese | 1320 | — |
| LMArena Korean | 1339 | — |
| LMArena Russian | 1377 | — |
| LMArena Spanish | 1375 | — |
Instruction Following Not comparable
GPT-4.1: 71.5 (#148), Llama 3.2 90B: —
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| IFEval | 83.8% | — |
| LMArena Instruction Following | 1367 | — |
Long Context Not comparable
GPT-4.1: 40.0 (#158), Llama 3.2 90B: —
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| Fiction.LiveBench | 63.9% | — |
| LMArena Longer Query | 1385 | — |
Writing & Preference Not comparable
GPT-4.1: 57.8 (#120), Llama 3.2 90B: —
| Benchmark | GPT-4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1383 | — |
| LMArena Creative Writing | 1363 | — |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LMArena Multi-Turn | 1398 | — |
Frequently asked questions
Is GPT-4.1 better than Llama 3.2 90B?
GPT-4.1 is the stronger model overall, scoring 35.7 to 27.1 on the Noometry Index.
How many benchmarks do GPT-4.1 and Llama 3.2 90B share?
7 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Llama 3.2 90B has 9.