Model comparison
Codellama 34b Instruct vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 30.2 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Tulu 3 (Tülu 3) 70B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.8 to 28.4.
Side by side
| Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 30.2 | 32.6 |
| Released | — | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Codellama 34b Instruct: 28.0 (#310), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1046 | 1236 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Codellama 34b Instruct: 18.8 (#250), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1220 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#227), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1056 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Not comparable
Codellama 34b Instruct: —, Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
Multilingual Tulu 3 (Tülu 3) 70B leads
Codellama 34b Instruct: 25.9 (#279), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1011 | 1236 |
| LMArena Chinese | 976 | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Codellama 34b Instruct: 52.4 (#286), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Codellama 34b Instruct: 30.8 (#279), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1014 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Codellama 34b Instruct: 28.4 (#292), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Codellama 34b Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1066 | 1256 |
| LMArena Creative Writing | 1032 | 1231 |
| LMArena Multi-Turn | 1015 | 1252 |
Frequently asked questions
Is Codellama 34b Instruct better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 30.2 on the Noometry Index.
Is Codellama 34b Instruct or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Tulu 3 (Tülu 3) 70B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.