Model comparison
Llama 2-13B vs o1
o1 is the stronger model overall, scoring 40.9 to 29.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o1 leads 55.6 to 29.8.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 74.7% for o1.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-13B | o1 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 29.6 | 40.9 |
| Released | 2023-07-18 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $60 |
| Results tracked | 32 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Llama 2-13B: 30.9 (#291), o1: 46.1 (#70)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Coding | 1062 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
Llama 2-13B: —, o1: 24.6 (#117)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Llama 2-13B: 12.8 (#337), o1: 27.9 (#111)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| Chess Puzzles | 0% | 15% |
| LMArena Hard Prompts | 1051 | 1371 |
| DTBench | 42.2% | 74.7% |
| Epoch Capabilities Index | 106.17 | 141.91 |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| BIG-Bench Hard | 58.2% | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| LiveBench | — | 75.7% |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math o1 leads
Llama 2-13B: 31.1 (#229), o1: 36.1 (#175)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Math | 1065 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
| GSM8K | 36.9% | — |
Knowledge o1 leads
Llama 2-13B: 28.1 (#249), o1: 41.5 (#110)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Expert | 1030 | 1361 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, o1: 34.2 (#93)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| ScienceQA | 55.8% | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Llama 2-13B: 26.5 (#279), o1: 48.6 (#142)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Non-English | 1024 | 1358 |
| LMArena Chinese | 1001 | 1394 |
| LMArena French | 1044 | 1344 |
| LMArena German | 1009 | 1337 |
| LMArena Japanese | 894 | 1346 |
| LMArena Korean | 953 | 1396 |
| LMArena Russian | 1055 | 1356 |
| LMArena Spanish | 1087 | 1345 |
Instruction Following o1 leads
Llama 2-13B: 53.3 (#287), o1: 74.8 (#86)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Instruction Following | 1045 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Llama 2-13B: 32.3 (#269), o1: 50.3 (#9)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Longer Query | 1064 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Llama 2-13B: 29.8 (#289), o1: 55.6 (#144)
| Benchmark | Llama 2-13B | o1 |
|---|---|---|
| LMArena Text | 1084 | 1366 |
| LMArena Creative Writing | 1047 | 1348 |
| LMArena Multi-Turn | 1050 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Llama 2-13B better than o1?
o1 is the stronger model overall, scoring 40.9 to 29.6 on the Noometry Index.
Is Llama 2-13B or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and o1 share?
20 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and o1 has 52.