Model comparison
Tulu 3 (Tülu 3) 70B vs Yi-34B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 27.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. Tulu 3 (Tülu 3) 70B scores higher in 7 categories and Yi-34B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Tulu 3 (Tülu 3) 70B leads 25.0 to 7.5.
- The biggest single-benchmark swing is MATH Level 5: 42.7% for Tulu 3 (Tülu 3) 70B and 5.1% for Yi-34B.
Side by side
| Tulu 3 (Tülu 3) 70B | Yi-34B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | 01.AI |
| Noometry Index | 33.0 | 27.8 |
| Released | 2024-11-21 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 23 |
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: 36.0 (#214), Yi-34B: 32.3 (#274)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| LMArena Coding | 1235 | 1112 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 23.9 (#169), Yi-34B: 21.2 (#226)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Yi-34B leads
Tulu 3 (Tülu 3) 70B: 14.2 (#303), Yi-34B: 21.6 (#282)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| LMArena Math | 1242 | 1114 |
| MATH Level 5 | 42.7% | 5.1% |
| OTIS Mock AIME 2024-2025 | 4.4% | — |
| GSM8K | — | 76% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 25.0 (#264), Yi-34B: 7.5 (#309)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| GPQA Diamond | 46.3% | 14.7% |
| LMArena Expert | — | 1061 |
| MMLU | — | 76.3% |
Multilingual Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 39.9 (#222), Yi-34B: 29.7 (#264)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1236 | 1079 |
| LMArena Chinese | 1249 | 1176 |
| LMArena Russian | 1246 | 1050 |
| LMArena French | — | 1081 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Spanish | — | 1070 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 64.8 (#227), Yi-34B: 56.2 (#274)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1233 | 1091 |
Long Context Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 37.1 (#222), Yi-34B: 33.2 (#264)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1224 | 1094 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Tulu 3 (Tülu 3) 70B: 45.6 (#223), Yi-34B: 34.1 (#273)
| Benchmark | Tulu 3 (Tülu 3) 70B | Yi-34B |
|---|---|---|
| LMArena Text | 1256 | 1129 |
| LMArena Creative Writing | 1231 | 1108 |
| LMArena Multi-Turn | 1252 | 1113 |
Frequently asked questions
Is Tulu 3 (Tülu 3) 70B better than Yi-34B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 27.8 on the Noometry Index.
Is Tulu 3 (Tülu 3) 70B or Yi-34B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 32.3 in the Noometry coding category.
How many benchmarks do Tulu 3 (Tülu 3) 70B and Yi-34B share?
13 benchmarks have published results for both models. Tulu 3 (Tülu 3) 70B has 14 scored results on Noometry and Yi-34B has 23.