Model comparison
Llama 3.1-405B vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 30.7 on the Noometry Index.
Last verified . 27 shared benchmarks.
MetaSummary
- They share 27 benchmarks with published results for both. Llama 3.1-405B scores higher in 2 categories and o3-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o3-mini leads 50.3 to 38.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 9.7% for Llama 3.1-405B and 76.9% for o3-mini.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | o3-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.7 | 36.7 |
| Released | 2024-07-23 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 42 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Llama 3.1-405B: 33.1 (#262), o3-mini: 40.8 (#132)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| WeirdML | 21.4% | 43.7% |
| LMArena Coding | 1291 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use o3-mini leads
Llama 3.1-405B: 21.0 (#140), o3-mini: 29.6 (#84)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| Cybench | 7.5% | 22.5% |
| TheAgentCompany | 7.4% | — |
Reasoning Too close to call
Llama 3.1-405B: 16.8 (#300), o3-mini: 16.3 (#305)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| SimpleBench | 23% | 22.8% |
| LMArena Hard Prompts | 1269 | 1366 |
| DTBench | 61.4% | 68.8% |
| Epoch Capabilities Index | 128.75 | 140.34 |
| ForecastBench | 59.9 | 59.6 |
| ARC-AGI-2 | — | 3% |
| Kagi LLM Benchmark | 45% | — |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| BIG-Bench Hard | 82.9% | — |
| HellaSwag | 89.2% | — |
| LiveBench | — | 75.9% |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math o3-mini leads
Llama 3.1-405B: 18.4 (#290), o3-mini: 28.1 (#244)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 76.9% |
| LMArena Math | 1281 | 1396 |
| MATH Level 5 | 49.8% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 24.9% | — |
| LiveBench Math | — | 77.3% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Llama 3.1-405B: 30.4 (#227), o3-mini: 38.3 (#146)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| GPQA Diamond | 50.9% | 77% |
| Confabulations | 17.6% | 17.9% |
| LMArena Expert | 1243 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 72.3% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual o3-mini leads
Llama 3.1-405B: 40.7 (#214), o3-mini: 45.7 (#164)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| LMArena Non-English | 1248 | 1319 |
| LMArena Chinese | 1242 | 1379 |
| LMArena French | 1279 | 1334 |
| LMArena German | 1252 | 1303 |
| LMArena Japanese | 1208 | 1286 |
| LMArena Korean | 1184 | 1314 |
| LMArena Russian | 1265 | 1304 |
| LMArena Spanish | 1260 | 1321 |
Instruction Following o3-mini leads
Llama 3.1-405B: 65.9 (#214), o3-mini: 75.1 (#72)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1259 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), o3-mini: 33.8 (#256)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| LMArena Longer Query | 1266 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Llama 3.1-405B: 38.9 (#251), o3-mini: 50.3 (#182)
| Benchmark | Llama 3.1-405B | o3-mini |
|---|---|---|
| LMArena Text | 1284 | 1337 |
| LMArena Creative Writing | 1262 | 1286 |
| LMArena Multi-Turn | 1297 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Llama 3.1-405B better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and o3-mini share?
27 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and o3-mini has 51.