Model comparison
Llama 3.2 90B vs Llama 3-8B
Llama 3.2 90B is the stronger model overall, scoring 27.1 to 25.3 on the Noometry Index.
Last verified . 5 shared benchmarks.
MetaSummary
- They share 5 benchmarks with published results for both. Llama 3.2 90B scores higher in 3 categories and Llama 3-8B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 90B leads 21.7 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 39.4% for Llama 3.2 90B and 6.1% for Llama 3-8B.
Side by side
| Llama 3.2 90B | Llama 3-8B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 27.1 | 25.3 |
| Released | 2024-09-24 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 9 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Llama 3-8B: 30.5 (#285)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | — | 31.9% |
| LMArena Coding | — | 1152 |
| BigCodeBench Complete | — | 36.9% |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 29.7 (#73), Llama 3-8B: —
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| BALROG | 27.3% | — |
Reasoning Llama 3.2 90B leads
Llama 3.2 90B: 20.9 (#207), Llama 3-8B: 13.8 (#321)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 116.33 |
| Chess Puzzles | — | 0% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1133 |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Llama 3.2 90B leads
Llama 3.2 90B: 10.4 (#302), Llama 3-8B: 8.3 (#317)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 1.9% |
| MATH Level 5 | 39.4% | 6.1% |
| LMArena Math | — | 1151 |
Knowledge Llama 3.2 90B leads
Llama 3.2 90B: 21.7 (#269), Llama 3-8B: 7.8 (#303)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 41% | 26.1% |
| MMLU | 80.3% | 68.8% |
| LMArena Expert | — | 1113 |
| ARC (AI2) Challenge | — | 82.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multimodal Not comparable
Llama 3.2 90B: 24.9 (#119), Llama 3-8B: —
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Llama 3-8B: 31.0 (#256)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| LMArena Non-English | — | 1098 |
| LMArena Chinese | — | 1076 |
| LMArena French | — | 1158 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1003 |
| LMArena Russian | — | 1109 |
| LMArena Spanish | — | 1172 |
Instruction Following Not comparable
Llama 3.2 90B: —, Llama 3-8B: 58.7 (#255)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | — | 1127 |
Long Context Not comparable
Llama 3.2 90B: —, Llama 3-8B: 34.2 (#246)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | — | 1128 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Llama 3-8B: 37.7 (#251)
| Benchmark | Llama 3.2 90B | Llama 3-8B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1150 |
| LMArena Multi-Turn | — | 1152 |
Frequently asked questions
Is Llama 3.2 90B better than Llama 3-8B?
Llama 3.2 90B is the stronger model overall, scoring 27.1 to 25.3 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Llama 3-8B share?
5 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Llama 3-8B has 34.