Model comparison
Llama 3.1-405B vs o1
o1 is the stronger model overall, scoring 40.9 to 30.7 on the Noometry Index.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and o1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o1 leads 36.1 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 9.7% for Llama 3.1-405B and 73.3% for o1.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | o1 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.7 | 40.9 |
| Released | 2024-07-23 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $60 |
| Results tracked | 42 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Llama 3.1-405B: 33.1 (#262), o1: 46.1 (#70)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| WeirdML | 21.4% | 47.6% |
| LMArena Coding | 1291 | 1367 |
| Aider Polyglot | — | 61.7% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use o1 leads
Llama 3.1-405B: 21.0 (#140), o1: 24.6 (#117)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| Cybench | 7.5% | 10% |
| TheAgentCompany | 7.4% | — |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Llama 3.1-405B: 16.8 (#300), o1: 27.9 (#111)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| SimpleBench | 23% | 41.7% |
| LMArena Hard Prompts | 1269 | 1371 |
| DTBench | 61.4% | 74.7% |
| Epoch Capabilities Index | 128.75 | 141.91 |
| Kagi LLM Benchmark | 45% | — |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| BIG-Bench Hard | 82.9% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| LiveBench | — | 75.7% |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math o1 leads
Llama 3.1-405B: 18.4 (#290), o1: 36.1 (#175)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 73.3% |
| LMArena Math | 1281 | 1388 |
| MATH Level 5 | 49.8% | 94.7% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| Omni-MATH | 24.9% | — |
| LiveBench Math | — | 80.3% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge o1 leads
Llama 3.1-405B: 30.4 (#227), o1: 41.5 (#110)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| GPQA Diamond | 50.9% | 76.8% |
| Confabulations | 17.6% | 11.7% |
| LMArena Expert | 1243 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 72.3% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multimodal Not comparable
Llama 3.1-405B: —, o1: 34.2 (#93)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Llama 3.1-405B: 40.7 (#214), o1: 48.6 (#142)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| LMArena Non-English | 1248 | 1358 |
| LMArena Chinese | 1242 | 1394 |
| LMArena French | 1279 | 1344 |
| LMArena German | 1252 | 1337 |
| LMArena Japanese | 1208 | 1346 |
| LMArena Korean | 1184 | 1396 |
| LMArena Russian | 1265 | 1356 |
| LMArena Spanish | 1260 | 1345 |
Instruction Following o1 leads
Llama 3.1-405B: 65.9 (#214), o1: 74.8 (#86)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| LMArena Instruction Following | 1259 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 81.1% | — |
Long Context o1 leads
Llama 3.1-405B: 38.4 (#197), o1: 50.3 (#9)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| LMArena Longer Query | 1266 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Llama 3.1-405B: 38.9 (#251), o1: 55.6 (#144)
| Benchmark | Llama 3.1-405B | o1 |
|---|---|---|
| LMArena Text | 1284 | 1366 |
| LMArena Creative Writing | 1262 | 1348 |
| LMArena Multi-Turn | 1297 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Llama 3.1-405B better than o1?
o1 is the stronger model overall, scoring 40.9 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and o1 share?
26 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and o1 has 52.