Model comparison
Llama 3.1-70B vs Llama 3.2 1B
Llama 3.1-70B is the stronger model overall, scoring 29.6 to 20.1 on the Noometry Index. Llama 3.2 1B costs 5.7× less per token, which makes it the better buy when Llama 3.1-70B's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. Llama 3.1-70B scores higher in 9 categories and Llama 3.2 1B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-70B leads 24.2 to 7.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 54.8% for Llama 3.1-70B and 11.3% for Llama 3.2 1B.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.40 / $0.40 for Llama 3.1-70B.
- Llama 3.1-70B accepts more context: 128K tokens versus 60K.
Side by side
| Llama 3.1-70B | Llama 3.2 1B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 29.6 | 20.1 |
| Released | 2024-07-23 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 128K | 60K |
| Max output | 4K | 54K |
| Input $ / M tokens | $0.40 | $0.027 |
| Output $ / M tokens | $0.40 | $0.20 |
| Results tracked | 35 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-70B leads
Llama 3.1-70B: 30.3 (#296), Llama 3.2 1B: 21.1 (#338)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| BigCodeBench Instruct | 46.1% | 8.2% |
| LMArena Coding | 1260 | 1070 |
| BigCodeBench Complete | 54.8% | 11.3% |
| WeirdML | 9% | — |
Agentic & Tool Use Llama 3.1-70B leads
Llama 3.1-70B: 25.1 (#112), Llama 3.2 1B: 14.6 (#150)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| BALROG | 27.9% | 6.6% |
| Berkeley Function Calling Leaderboard | — | 10.8% |
| TheAgentCompany | 6.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), Llama 3.2 1B: 16.2 (#308)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1044 |
| Epoch Capabilities Index | 125.92 | 101.99 |
| Chess Puzzles | — | 0% |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
Math Llama 3.1-70B leads
Llama 3.1-70B: 13.5 (#304), Llama 3.2 1B: 10.4 (#313)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | 0.6% |
| LMArena Math | 1252 | 1086 |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Llama 3.1-70B leads
Llama 3.1-70B: 24.2 (#269), Llama 3.2 1B: 7.2 (#312)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | 44.2% | 23.9% |
| LMArena Expert | 1209 | 1007 |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.8 (#225), Llama 3.2 1B: 23.8 (#292)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 1219 | 973 |
| LMArena Chinese | 1215 | 959 |
| LMArena German | 1222 | 1014 |
| LMArena Russian | 1234 | 941 |
| LMArena French | 1261 | — |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.3 (#223), Llama 3.2 1B: 52.4 (#290)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 1231 | 1031 |
| IFEval | 82.1% | — |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#214), Llama 3.2 1B: 31.9 (#274)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 1241 | 1050 |
Writing & Preference Llama 3.1-70B leads
Llama 3.1-70B: 35.4 (#267), Llama 3.2 1B: 21.3 (#310)
| Benchmark | Llama 3.1-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1261 | 1055 |
| LMArena Creative Writing | 1232 | 1033 |
| EQ-Bench Creative Writing | 784 | 200 |
| LMArena Multi-Turn | 1256 | 1030 |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Llama 3.2 1B?
Llama 3.1-70B is the stronger model overall, scoring 29.6 to 20.1 on the Noometry Index. Llama 3.2 1B costs 5.7× less per token, which makes it the better buy when Llama 3.1-70B's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-70B or Llama 3.2 1B?
Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Llama 3.1-70B lists at $0.40 and $0.40.
Is Llama 3.1-70B or Llama 3.2 1B better for coding?
Llama 3.1-70B scores higher on coding benchmarks: 30.3 versus 21.1 in the Noometry coding category.
Which has the bigger context window?
Llama 3.1-70B does, with 128K tokens against 60K.
How many benchmarks do Llama 3.1-70B and Llama 3.2 1B share?
20 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Llama 3.2 1B has 22.