Model comparison
Llama 3-70B vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 28.8 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. Llama 3-70B scores higher in 2 categories and o1-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 12.8.
- The biggest single-benchmark swing is MATH Level 5: 22.6% for Llama 3-70B and 89.2% for o1-mini.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | o1-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 28.8 | 34.0 |
| Released | 2024-04-18 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-70B: 35.8 (#218), o1-mini: 35.5 (#224)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| LMArena Coding | 1206 | 1362 |
| HumanEval+ | 72% | 89% |
| MBPP+ | 69% | 78.8% |
| Aider Polyglot | — | 32.9% |
| WeirdML | — | 36.3% |
| BigCodeBench Instruct | 43.6% | — |
| LiveBench Coding | — | 48% |
| BigCodeBench Complete | 54.5% | — |
Agentic & Tool Use o1-mini leads
Llama 3-70B: 21.1 (#139), o1-mini: 24.6 (#118)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| Cybench | 5% | 10% |
Reasoning Llama 3-70B leads
Llama 3-70B: 18.0 (#288), o1-mini: 8.8 (#346)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1333 |
| Epoch Capabilities Index | 122.93 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 35.1% | — |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 54.2% | — |
| LiveBench Data Analysis | — | 57.9% |
| ForecastBench | 57.1 | — |
| LiveBench | — | 57.8% |
| WinoGrande | 83.5% | — |
Math o1-mini leads
Llama 3-70B: 12.8 (#305), o1-mini: 35.4 (#186)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 46.9% |
| LMArena Math | 1218 | 1358 |
| MATH Level 5 | 22.6% | 89.2% |
| LiveBench Math | — | 62% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge o1-mini leads
Llama 3-70B: 20.8 (#277), o1-mini: 34.9 (#192)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| GPQA Diamond | 40.6% | 62.4% |
| LMArena Expert | 1149 | 1316 |
| Confabulations | — | 18.6% |
| MMLU | 79.3% | — |
Multilingual o1-mini leads
Llama 3-70B: 33.6 (#251), o1-mini: 43.6 (#182)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| LMArena Non-English | 1142 | 1289 |
| LMArena Chinese | 1114 | 1314 |
| LMArena French | 1232 | 1293 |
| LMArena German | 1169 | 1278 |
| LMArena Japanese | 1017 | 1245 |
| LMArena Korean | 1017 | 1223 |
| LMArena Russian | 1159 | 1283 |
| LMArena Spanish | 1241 | 1303 |
Instruction Following o1-mini leads
Llama 3-70B: 62.5 (#238), o1-mini: 66.7 (#206)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1194 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context o1-mini leads
Llama 3-70B: 35.6 (#240), o1-mini: 40.1 (#161)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| LMArena Longer Query | 1174 | 1320 |
Writing & Preference o1-mini leads
Llama 3-70B: 42.8 (#231), o1-mini: 48.4 (#202)
| Benchmark | Llama 3-70B | o1-mini |
|---|---|---|
| LMArena Text | 1221 | 1317 |
| LMArena Creative Writing | 1210 | 1244 |
| LMArena Multi-Turn | 1223 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Llama 3-70B better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 28.8 on the Noometry Index.
Is Llama 3-70B or o1-mini better for coding?
They score almost the same on coding (35.8 vs 35.5); test both on your own repository before choosing.
How many benchmarks do Llama 3-70B and o1-mini share?
24 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and o1-mini has 39.