Model comparison
Llama 3.2 3B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 28.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Llama 3.2 3B scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 24.7.
Side by side
| Llama 3.2 3B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 28.9 | 33.0 |
| Released | 2024-09-24 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Llama 3.2 3B: 27.6 (#319), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1098 | 1235 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Llama 3.2 3B: 21.0 (#228), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1220 |
Math Llama 3.2 3B leads
Llama 3.2 3B: 32.4 (#214), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1126 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1090 | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Llama 3.2 3B: 26.2 (#281), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1019 | 1236 |
| LMArena Chinese | 1017 | 1249 |
| LMArena Russian | 949 | 1246 |
| LMArena German | 1056 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Llama 3.2 3B: 56.0 (#275), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1089 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Llama 3.2 3B: 33.4 (#261), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1100 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Llama 3.2 3B: 24.7 (#307), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Llama 3.2 3B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1110 | 1256 |
| LMArena Creative Writing | 1094 | 1231 |
| LMArena Multi-Turn | 1105 | 1252 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 28.9 on the Noometry Index.
Is Llama 3.2 3B or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.