Model comparison
Llama 3.2 1B vs Llama-3.3-70B-Instruct
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 20.1 on the Noometry Index. Llama 3.2 1B costs 2.2× less per token, which makes it the better buy when Llama-3.3-70B-Instruct's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. Llama 3.2 1B scores higher in 2 categories and Llama-3.3-70B-Instruct in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama-3.3-70B-Instruct leads 47.6 to 21.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 57.5% for Llama-3.3-70B-Instruct.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.10 / $0.32 for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct accepts more context: 128K tokens versus 60K.
Side by side
| Llama 3.2 1B | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 20.1 | 30.6 |
| Released | 2024-09-24 | 2024-12-06 |
| Weights | Open | Open |
| Context window | 60K | 128K |
| Max output | 54K | 4K |
| Input $ / M tokens | $0.027 | $0.10 |
| Output $ / M tokens | $0.20 | $0.32 |
| Results tracked | 22 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Llama 3.2 1B: 21.1 (#338), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| BigCodeBench Instruct | 8.2% | 46.9% |
| LMArena Coding | 1070 | 1268 |
| BigCodeBench Complete | 11.3% | 57.5% |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| LiveBench Coding | — | 36.6% |
Agentic & Tool Use Llama-3.3-70B-Instruct leads
Llama 3.2 1B: 14.6 (#150), Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | 31.9% |
| BALROG | 6.6% | 23% |
Reasoning Llama 3.2 1B leads
Llama 3.2 1B: 16.2 (#308), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1257 |
| Epoch Capabilities Index | 101.99 | 127.33 |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 50.8% |
| DTBench | — | 59.5% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| ForecastBench | — | 58.6 |
| LiveBench | — | 50.2% |
Math Llama-3.3-70B-Instruct leads
Llama 3.2 1B: 10.4 (#313), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 5.1% |
| LMArena Math | 1086 | 1267 |
| LiveBench Math | — | 42.2% |
| MATH Level 5 | — | 41.6% |
Knowledge Llama-3.3-70B-Instruct leads
Llama 3.2 1B: 7.2 (#312), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 23.9% | 47.4% |
| LMArena Expert | 1007 | 1225 |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| MMLU | — | 86.3% |
Multilingual Llama-3.3-70B-Instruct leads
Llama 3.2 1B: 23.8 (#292), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 973 | 1236 |
| LMArena Chinese | 959 | 1217 |
| LMArena German | 1014 | 1251 |
| LMArena Russian | 941 | 1252 |
| LMArena French | — | 1281 |
| LMArena Japanese | — | 1150 |
| LMArena Korean | — | 1143 |
| LMArena Spanish | — | 1270 |
Instruction Following Llama-3.3-70B-Instruct leads
Llama 3.2 1B: 52.4 (#290), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1031 | 1242 |
| LiveBench Instruction Following | — | 82.7% |
Long Context Llama 3.2 1B leads
Llama 3.2 1B: 31.9 (#274), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1050 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama 3.2 1B: 21.3 (#310), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | Llama 3.2 1B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1055 | 1274 |
| LMArena Creative Writing | 1033 | 1250 |
| LMArena Multi-Turn | 1030 | 1280 |
| EQ-Bench Creative Writing | 200 | — |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is Llama 3.2 1B better than Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 20.1 on the Noometry Index. Llama 3.2 1B costs 2.2× less per token, which makes it the better buy when Llama-3.3-70B-Instruct's lead doesn't matter for your workload.
Which is cheaper, Llama 3.2 1B or Llama-3.3-70B-Instruct?
Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Llama-3.3-70B-Instruct lists at $0.10 and $0.32.
Is Llama 3.2 1B or Llama-3.3-70B-Instruct better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 21.1 in the Noometry coding category.
Which has the bigger context window?
Llama-3.3-70B-Instruct does, with 128K tokens against 60K.
How many benchmarks do Llama 3.2 1B and Llama-3.3-70B-Instruct share?
20 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Llama-3.3-70B-Instruct has 43.