Model comparison
Palm 2 vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 29.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. Palm 2 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 25.7.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 29.4 | 32.6 |
| Released | — | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Palm 2: 28.5 (#306), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 995 | 1236 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Palm 2: 18.2 (#270), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1220 |
Math Palm 2 leads
Palm 2: 28.4 (#229), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1049 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Not comparable
Palm 2: —, Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
Multilingual Tulu 3 (Tülu 3) 70B leads
Palm 2: 21.1 (#290), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 916 | 1236 |
| LMArena Chinese | 887 | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Palm 2: 51.3 (#291), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1010 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Palm 2: 30.7 (#280), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1010 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Palm 2: 25.7 (#299), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Palm 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1027 | 1256 |
| LMArena Creative Writing | 991 | 1231 |
| LMArena Multi-Turn | 994 | 1252 |
Frequently asked questions
Is Palm 2 better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 29.4 on the Noometry Index.
Is Palm 2 or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 28.5 in the Noometry coding category.
How many benchmarks do Palm 2 and Tulu 3 (Tülu 3) 70B share?
10 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.