Model comparison
Tulu 3 (Tülu 3) 70B vs Wizardlm 13b
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Allen Institute for AI (Ai2)
MicrosoftSummary
- They share 10 benchmarks with published results for both. Tulu 3 (Tülu 3) 70B scores higher in 6 categories and Wizardlm 13b in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.8 to 30.7.
Side by side
| Tulu 3 (Tülu 3) 70B | Wizardlm 13b | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 32.6 | 30.8 |
| Released | 2024-11-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 35.4 (#211), Wizardlm 13b: 29.6 (#293)
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 1236 | 1035 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 22.9 (#172), Wizardlm 13b: 18.5 (#265)
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1018 |
Math Wizardlm 13b leads
Tulu 3 (Tülu 3) 70B: 13.3 (#297), Wizardlm 13b: 27.8 (#235)
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| LMArena Math | 1242 | 1017 |
| OTIS Mock AIME 2024-2025 | 4.4% | — |
| MATH Level 5 | 42.7% | — |
Knowledge Not comparable
Tulu 3 (Tülu 3) 70B: 25.1 (#257), Wizardlm 13b: —
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| GPQA Diamond | 46.3% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 40.1 (#217), Wizardlm 13b: 27.3 (#272)
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 1236 | 1034 |
| LMArena Chinese | 1249 | 1023 |
| LMArena Russian | 1246 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 65.0 (#222), Wizardlm 13b: 53.7 (#280)
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 1233 | 1049 |
Long Context Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 37.1 (#217), Wizardlm 13b: 32.0 (#268)
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | 1224 | 1054 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 45.8 (#218), Wizardlm 13b: 30.7 (#282)
| Benchmark | Tulu 3 (Tülu 3) 70B | Wizardlm 13b |
|---|---|---|
| LMArena Text | 1256 | 1077 |
| LMArena Creative Writing | 1231 | 1090 |
| LMArena Multi-Turn | 1252 | 1047 |
Frequently asked questions
Is Tulu 3 (Tülu 3) 70B better than Wizardlm 13b?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 30.8 on the Noometry Index.
Is Tulu 3 (Tülu 3) 70B or Wizardlm 13b better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 29.6 in the Noometry coding category.
How many benchmarks do Tulu 3 (Tülu 3) 70B and Wizardlm 13b share?
10 benchmarks have published results for both models. Tulu 3 (Tülu 3) 70B has 14 scored results on Noometry and Wizardlm 13b has 10.