Model comparison
Llama 13b vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
MetaSummary
- They share 9 benchmarks with published results for both. Llama 13b scores higher in 1 category and o1-mini in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o1-mini leads 48.4 to 13.8.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| Llama 13b | o1-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 24.4 | 34.0 |
| Released | 2023-02-24 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
Llama 13b: 21.4 (#337), o1-mini: 35.5 (#224)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| LMArena Coding | 683 | 1362 |
| Aider Polyglot | — | 32.9% |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
Llama 13b: —, o1-mini: 24.6 (#118)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning Llama 13b leads
Llama 13b: 14.0 (#329), o1-mini: 8.8 (#346)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 728 | 1333 |
| Epoch Capabilities Index | 100.58 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| LiveBench Data Analysis | — | 57.9% |
| BIG-Bench Hard | 37.9% | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| LiveBench | — | 57.8% |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math o1-mini leads
Llama 13b: 26.7 (#256), o1-mini: 35.4 (#186)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| LMArena Math | 838 | 1358 |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, o1-mini: 34.9 (#192)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| LMArena Expert | — | 1316 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, o1-mini: —
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual o1-mini leads
Llama 13b: 16.6 (#297), o1-mini: 43.6 (#182)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| LMArena Non-English | 819 | 1289 |
| LMArena Chinese | — | 1314 |
| LMArena French | — | 1293 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
| LMArena Russian | — | 1283 |
| LMArena Spanish | — | 1303 |
Instruction Following o1-mini leads
Llama 13b: 36.7 (#305), o1-mini: 66.7 (#206)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| LMArena Instruction Following | 781 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context Not comparable
Llama 13b: —, o1-mini: 40.1 (#161)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| LMArena Longer Query | — | 1320 |
Writing & Preference o1-mini leads
Llama 13b: 13.8 (#312), o1-mini: 48.4 (#202)
| Benchmark | Llama 13b | o1-mini |
|---|---|---|
| LMArena Text | 834 | 1317 |
| LMArena Creative Writing | 794 | 1244 |
| LMArena Multi-Turn | 753 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Llama 13b better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 24.4 on the Noometry Index.
Is Llama 13b or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and o1-mini share?
9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and o1-mini has 39.