Model comparison
Llama 3.2 90B vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 27.1 on the Noometry Index.
Last verified . 7 shared benchmarks.
MetaSummary
- They share 7 benchmarks with published results for both. Llama 3.2 90B scores higher in 0 categories and o4-mini in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where o4-mini leads 40.2 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 81.7% for o4-mini.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | o4-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 27.1 | 41.6 |
| Released | 2024-09-24 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 9 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, o4-mini: 41.6 (#110)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| LMArena Coding | — | 1369 |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Llama 3.2 90B: 29.7 (#73), o4-mini: 32.3 (#57)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| BALROG | 27.3% | — |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Llama 3.2 90B: 20.9 (#207), o4-mini: 24.6 (#143)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| EnigmaEval | 0.4% | 9.2% |
| Epoch Capabilities Index | 125.5 | 145.63 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| LMArena Hard Prompts | — | 1351 |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| ForecastBench | — | 61.8 |
Math o4-mini leads
Llama 3.2 90B: 10.4 (#302), o4-mini: 40.2 (#79)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 81.7% |
| MATH Level 5 | 39.4% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| Omni-MATH | — | 72% |
| LMArena Math | — | 1390 |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Llama 3.2 90B: 21.7 (#269), o4-mini: 43.5 (#83)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| GPQA Diamond | 41% | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
| LMArena Expert | — | 1344 |
| MMLU | 80.3% | — |
Multimodal o4-mini leads
Llama 3.2 90B: 24.9 (#119), o4-mini: 39.5 (#46)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| LMArena Vision | 1000 | 1194 |
| GeoBench | 52% | 64% |
| VPCT | — | 57.5% |
Multilingual Not comparable
Llama 3.2 90B: —, o4-mini: 47.2 (#149)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| LMArena Non-English | — | 1336 |
| LMArena Chinese | — | 1355 |
| LMArena French | — | 1362 |
| LMArena German | — | 1336 |
| LMArena Japanese | — | 1308 |
| LMArena Korean | — | 1313 |
| LMArena Russian | — | 1334 |
| LMArena Spanish | — | 1346 |
Instruction Following Not comparable
Llama 3.2 90B: —, o4-mini: 75.4 (#63)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| IFEval | — | 92.8% |
| LMArena Instruction Following | — | 1321 |
Long Context Not comparable
Llama 3.2 90B: —, o4-mini: 45.5 (#31)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| Fiction.LiveBench | — | 77.8% |
| LMArena Longer Query | — | 1315 |
Writing & Preference Not comparable
Llama 3.2 90B: —, o4-mini: 54.2 (#148)
| Benchmark | Llama 3.2 90B | o4-mini |
|---|---|---|
| LMArena Text | — | 1353 |
| LMArena Creative Writing | — | 1294 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
| LMArena Multi-Turn | — | 1350 |
Frequently asked questions
Is Llama 3.2 90B better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 27.1 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and o4-mini share?
7 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and o4-mini has 60.