Model comparison
Llama 3-8B vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 25.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. Llama 3-8B scores higher in 1 category and o3-mini in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 96.5% for o3-mini.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | o3-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 25.5 | 36.7 |
| Released | 2024-04-18 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Llama 3-8B: 31.0 (#289), o3-mini: 40.8 (#132)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| LMArena Coding | 1152 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 31.9% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 36.9% | — |
| CadEval | — | 54% |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3-8B: —, o3-mini: 29.6 (#84)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning o3-mini leads
Llama 3-8B: 14.3 (#326), o3-mini: 16.3 (#305)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| Chess Puzzles | 0% | 17% |
| LMArena Hard Prompts | 1133 | 1366 |
| DTBench | 43.9% | 68.8% |
| Epoch Capabilities Index | 116.45 | 140.34 |
| ForecastBench | 58.6 | 59.6 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| Adversarial NLI | 57.3% | — |
| LiveBench | — | 75.9% |
| WinoGrande | 75.7% | — |
Math o3-mini leads
Llama 3-8B: 8.8 (#323), o3-mini: 28.1 (#244)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 76.9% |
| LMArena Math | 1151 | 1396 |
| MATH Level 5 | 6.1% | 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% |
Knowledge o3-mini leads
Llama 3-8B: 7.8 (#308), o3-mini: 38.3 (#146)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| GPQA Diamond | 26.1% | 77% |
| LMArena Expert | 1113 | 1364 |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual o3-mini leads
Llama 3-8B: 30.8 (#261), o3-mini: 45.7 (#164)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| LMArena Non-English | 1098 | 1319 |
| LMArena Chinese | 1076 | 1379 |
| LMArena French | 1159 | 1334 |
| LMArena German | 1104 | 1303 |
| LMArena Japanese | 967 | 1286 |
| LMArena Korean | 1004 | 1314 |
| LMArena Russian | 1109 | 1304 |
| LMArena Spanish | 1173 | 1321 |
Instruction Following o3-mini leads
Llama 3-8B: 58.4 (#260), o3-mini: 75.1 (#72)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1127 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Too close to call
Llama 3-8B: 34.2 (#251), o3-mini: 33.8 (#256)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| LMArena Longer Query | 1128 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Llama 3-8B: 37.5 (#256), o3-mini: 50.3 (#182)
| Benchmark | Llama 3-8B | o3-mini |
|---|---|---|
| LMArena Text | 1166 | 1337 |
| LMArena Creative Writing | 1150 | 1286 |
| LMArena Multi-Turn | 1152 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Llama 3-8B better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 25.5 on the Noometry Index.
Is Llama 3-8B or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and o3-mini share?
24 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and o3-mini has 51.