Model comparison
Llama 2-70B vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 24.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and o3-mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 96.5% for o3-mini.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | o3-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 24.4 | 36.7 |
| Released | 2023-07-18 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 35 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Llama 2-70B: 31.4 (#286), o3-mini: 40.8 (#132)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| LMArena Coding | 1079 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
Llama 2-70B: —, o3-mini: 29.6 (#84)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning o3-mini leads
Llama 2-70B: 14.4 (#325), o3-mini: 16.3 (#305)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1366 |
| DTBench | 41.6% | 68.8% |
| Epoch Capabilities Index | 113.79 | 140.34 |
| ForecastBench | 51.4 | 59.6 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| LiveBench | — | 75.9% |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math o3-mini leads
Llama 2-70B: 8.1 (#326), o3-mini: 28.1 (#244)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 76.9% |
| LMArena Math | 1091 | 1396 |
| MATH Level 5 | 3.3% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| LiveBench Math | — | 77.3% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
| GSM8K | 69.6% | — |
Knowledge o3-mini leads
Llama 2-70B: 7.4 (#310), o3-mini: 38.3 (#146)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| GPQA Diamond | 26.3% | 77% |
| LMArena Expert | 1039 | 1364 |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual o3-mini leads
Llama 2-70B: 27.7 (#274), o3-mini: 45.7 (#164)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| LMArena Non-English | 1045 | 1319 |
| LMArena Chinese | 995 | 1379 |
| LMArena French | 1090 | 1334 |
| LMArena German | 1041 | 1303 |
| LMArena Japanese | 927 | 1286 |
| LMArena Korean | 964 | 1314 |
| LMArena Russian | 1083 | 1304 |
| LMArena Spanish | 1143 | 1321 |
Instruction Following o3-mini leads
Llama 2-70B: 54.9 (#278), o3-mini: 75.1 (#72)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1071 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context o3-mini leads
Llama 2-70B: 32.3 (#270), o3-mini: 33.8 (#256)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| LMArena Longer Query | 1062 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Llama 2-70B: 32.3 (#279), o3-mini: 50.3 (#182)
| Benchmark | Llama 2-70B | o3-mini |
|---|---|---|
| LMArena Text | 1115 | 1337 |
| LMArena Creative Writing | 1075 | 1286 |
| LMArena Multi-Turn | 1088 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Llama 2-70B better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 24.4 on the Noometry Index.
Is Llama 2-70B or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and o3-mini share?
23 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and o3-mini has 51.