Model comparison
Llama 3.1-8B vs Llama 3.2 90B
Llama 3.2 90B is the stronger model overall, scoring 27.5 to 23.0 on the Noometry Index.
Last verified . 6 shared benchmarks.
MetaSummary
- They share 6 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Llama 3.2 90B in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 90B leads 21.7 to 8.0.
- The biggest single-benchmark swing is MATH Level 5: 22.9% for Llama 3.1-8B and 39.4% for Llama 3.2 90B.
Side by side
| Llama 3.1-8B | Llama 3.2 90B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 23.0 | 27.5 |
| Released | 2024-07-23 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 43 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1-8B: 20.2 (#340), Llama 3.2 90B: —
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| LMArena Coding | 1195 | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Llama 3.2 90B leads
Llama 3.1-8B: 22.5 (#131), Llama 3.2 90B: 30.0 (#80)
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| BALROG | 15.1% | 27.3% |
| Berkeley Function Calling Leaderboard | 25.8% | — |
Reasoning Llama 3.2 90B leads
Llama 3.1-8B: 14.9 (#321), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 116.57 | 125.5 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1175 | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| PIQA | 81.2% | — |
Math Too close to call
Llama 3.1-8B: 10.2 (#317), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 2.6% |
| MATH Level 5 | 22.9% | 39.4% |
| Omni-MATH | 13.7% | — |
| LMArena Math | 1179 | — |
| GSM8K | 82.4% | — |
Knowledge Llama 3.2 90B leads
Llama 3.1-8B: 8.0 (#307), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 27% | 41% |
| MMLU | 56.1% | 80.3% |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| LMArena Expert | 1144 | — |
| BoolQ | 82.8% | — |
Multimodal Not comparable
Llama 3.1-8B: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Llama 3.1-8B: 34.0 (#249), Llama 3.2 90B: —
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1148 | — |
| LMArena Chinese | 1151 | — |
| LMArena French | 1177 | — |
| LMArena German | 1144 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1053 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1169 | — |
Instruction Following Not comparable
Llama 3.1-8B: 58.9 (#258), Llama 3.2 90B: —
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| IFEval | 74.3% | — |
| LMArena Instruction Following | 1159 | — |
Long Context Not comparable
Llama 3.1-8B: 35.8 (#238), Llama 3.2 90B: —
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1182 | — |
Writing & Preference Not comparable
Llama 3.1-8B: 29.7 (#290), Llama 3.2 90B: —
| Benchmark | Llama 3.1-8B | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1154 | — |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
| LMArena Multi-Turn | 1172 | — |
Frequently asked questions
Is Llama 3.1-8B better than Llama 3.2 90B?
Llama 3.2 90B is the stronger model overall, scoring 27.5 to 23.0 on the Noometry Index.
How many benchmarks do Llama 3.1-8B and Llama 3.2 90B share?
6 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Llama 3.2 90B has 9.