Model comparison
Llama 3.2 1B vs Llama 3-8B
Llama 3-8B is the stronger model overall, scoring 25.5 to 20.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Llama 3.2 1B scores higher in 2 categories and Llama 3-8B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-8B leads 37.5 to 21.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 36.9% for Llama 3-8B.
Side by side
| Llama 3.2 1B | Llama 3-8B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 20.1 | 25.5 |
| Released | 2024-09-24 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 60K | — |
| Max output | 54K | — |
| Input $ / M tokens | $0.027 | — |
| Output $ / M tokens | $0.20 | — |
| Results tracked | 22 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-8B leads
Llama 3.2 1B: 21.1 (#338), Llama 3-8B: 31.0 (#289)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 8.2% | 31.9% |
| LMArena Coding | 1070 | 1152 |
| BigCodeBench Complete | 11.3% | 36.9% |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Agentic & Tool Use Not comparable
Llama 3.2 1B: 14.6 (#150), Llama 3-8B: —
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |
Reasoning Llama 3.2 1B leads
Llama 3.2 1B: 16.2 (#308), Llama 3-8B: 14.3 (#326)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1044 | 1133 |
| Epoch Capabilities Index | 101.99 | 116.45 |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Llama 3.2 1B leads
Llama 3.2 1B: 10.4 (#313), Llama 3-8B: 8.8 (#323)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 1.9% |
| LMArena Math | 1086 | 1151 |
| MATH Level 5 | — | 6.1% |
Knowledge Too close to call
Llama 3.2 1B: 7.2 (#312), Llama 3-8B: 7.8 (#308)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 23.9% | 26.1% |
| LMArena Expert | 1007 | 1113 |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Llama 3-8B leads
Llama 3.2 1B: 23.8 (#292), Llama 3-8B: 30.8 (#261)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 973 | 1098 |
| LMArena Chinese | 959 | 1076 |
| LMArena German | 1014 | 1104 |
| LMArena Russian | 941 | 1109 |
| LMArena French | — | 1159 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1004 |
| LMArena Spanish | — | 1173 |
Instruction Following Llama 3-8B leads
Llama 3.2 1B: 52.4 (#290), Llama 3-8B: 58.4 (#260)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1127 |
Long Context Llama 3-8B leads
Llama 3.2 1B: 31.9 (#274), Llama 3-8B: 34.2 (#251)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1050 | 1128 |
Writing & Preference Llama 3-8B leads
Llama 3.2 1B: 21.3 (#310), Llama 3-8B: 37.5 (#256)
| Benchmark | Llama 3.2 1B | Llama 3-8B |
|---|---|---|
| LMArena Text | 1055 | 1166 |
| LMArena Creative Writing | 1033 | 1150 |
| LMArena Multi-Turn | 1030 | 1152 |
| EQ-Bench Creative Writing | 200 | — |
Frequently asked questions
Is Llama 3.2 1B better than Llama 3-8B?
Llama 3-8B is the stronger model overall, scoring 25.5 to 20.1 on the Noometry Index.
Is Llama 3.2 1B or Llama 3-8B better for coding?
Llama 3-8B scores higher on coding benchmarks: 31.0 versus 21.1 in the Noometry coding category.
How many benchmarks do Llama 3.2 1B and Llama 3-8B share?
19 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Llama 3-8B has 34.