Model comparison
Llama 2-70B vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 24.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Llama 2-70B scores higher in 1 category and o1-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1-mini leads 34.9 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 89.2% for o1-mini.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | o1-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 24.4 | 34.0 |
| Released | 2023-07-18 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
Llama 2-70B: 31.4 (#286), o1-mini: 35.5 (#224)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| LMArena Coding | 1079 | 1362 |
| Aider Polyglot | — | 32.9% |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
Llama 2-70B: —, o1-mini: 24.6 (#118)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning Llama 2-70B leads
Llama 2-70B: 14.4 (#325), o1-mini: 8.8 (#346)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1333 |
| Epoch Capabilities Index | 113.79 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 41.6% | — |
| LiveBench Data Analysis | — | 57.9% |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| LiveBench | — | 57.8% |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math o1-mini leads
Llama 2-70B: 8.1 (#326), o1-mini: 35.4 (#186)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 46.9% |
| LMArena Math | 1091 | 1358 |
| MATH Level 5 | 3.3% | 89.2% |
| LiveBench Math | — | 62% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 69.6% | — |
Knowledge o1-mini leads
Llama 2-70B: 7.4 (#310), o1-mini: 34.9 (#192)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| GPQA Diamond | 26.3% | 62.4% |
| LMArena Expert | 1039 | 1316 |
| Confabulations | — | 18.6% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual o1-mini leads
Llama 2-70B: 27.7 (#274), o1-mini: 43.6 (#182)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| LMArena Non-English | 1045 | 1289 |
| LMArena Chinese | 995 | 1314 |
| LMArena French | 1090 | 1293 |
| LMArena German | 1041 | 1278 |
| LMArena Japanese | 927 | 1245 |
| LMArena Korean | 964 | 1223 |
| LMArena Russian | 1083 | 1283 |
| LMArena Spanish | 1143 | 1303 |
Instruction Following o1-mini leads
Llama 2-70B: 54.9 (#278), o1-mini: 66.7 (#206)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1071 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context o1-mini leads
Llama 2-70B: 32.3 (#270), o1-mini: 40.1 (#161)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| LMArena Longer Query | 1062 | 1320 |
Writing & Preference o1-mini leads
Llama 2-70B: 32.3 (#279), o1-mini: 48.4 (#202)
| Benchmark | Llama 2-70B | o1-mini |
|---|---|---|
| LMArena Text | 1115 | 1317 |
| LMArena Creative Writing | 1075 | 1244 |
| LMArena Multi-Turn | 1088 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Llama 2-70B better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 24.4 on the Noometry Index.
Is Llama 2-70B or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and o1-mini share?
21 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and o1-mini has 39.