Model comparison
Llama 3.2 1B vs Llama 3.2 90B
Llama 3.2 90B is the stronger model overall, scoring 27.5 to 20.1 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Llama 3.2 1B 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 agentic & tool use, where Llama 3.2 90B leads 30.0 to 14.6.
- The biggest single-benchmark swing is BALROG: 6.6% for Llama 3.2 1B and 27.3% for Llama 3.2 90B.
Side by side
| Llama 3.2 1B | Llama 3.2 90B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 20.1 | 27.5 |
| Released | 2024-09-24 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 60K | — |
| Max output | 54K | — |
| Input $ / M tokens | $0.027 | — |
| Output $ / M tokens | $0.20 | — |
| Results tracked | 22 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 1B: 21.1 (#338), Llama 3.2 90B: —
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| BigCodeBench Instruct | 8.2% | — |
| LMArena Coding | 1070 | — |
| BigCodeBench Complete | 11.3% | — |
Agentic & Tool Use Llama 3.2 90B leads
Llama 3.2 1B: 14.6 (#150), Llama 3.2 90B: 30.0 (#80)
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| BALROG | 6.6% | 27.3% |
| Berkeley Function Calling Leaderboard | 10.8% | — |
Reasoning Llama 3.2 90B leads
Llama 3.2 1B: 16.2 (#308), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 101.99 | 125.5 |
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1044 | — |
Math Too close to call
Llama 3.2 1B: 10.4 (#313), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 2.6% |
| LMArena Math | 1086 | — |
| MATH Level 5 | — | 39.4% |
Knowledge Llama 3.2 90B leads
Llama 3.2 1B: 7.2 (#312), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 23.9% | 41% |
| LMArena Expert | 1007 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
Llama 3.2 1B: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Llama 3.2 1B: 23.8 (#292), Llama 3.2 90B: —
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 973 | — |
| LMArena Chinese | 959 | — |
| LMArena German | 1014 | — |
| LMArena Russian | 941 | — |
Instruction Following Not comparable
Llama 3.2 1B: 52.4 (#290), Llama 3.2 90B: —
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1031 | — |
Long Context Not comparable
Llama 3.2 1B: 31.9 (#274), Llama 3.2 90B: —
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1050 | — |
Writing & Preference Not comparable
Llama 3.2 1B: 21.3 (#310), Llama 3.2 90B: —
| Benchmark | Llama 3.2 1B | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1055 | — |
| LMArena Creative Writing | 1033 | — |
| EQ-Bench Creative Writing | 200 | — |
| LMArena Multi-Turn | 1030 | — |
Frequently asked questions
Is Llama 3.2 1B better than Llama 3.2 90B?
Llama 3.2 90B is the stronger model overall, scoring 27.5 to 20.1 on the Noometry Index.
How many benchmarks do Llama 3.2 1B and Llama 3.2 90B share?
4 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Llama 3.2 90B has 9.