Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B has enough public results to be ranked (#242); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 35.4.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 39.7 | 32.6 |
| Released | 2024-05-07 | 2024-11-21 |
| Weights | Open | 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 DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1236 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | — | 1220 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B has enough public results to be ranked (#242); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Tulu 3 (Tülu 3) 70B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 35.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Tulu 3 (Tülu 3) 70B share?
0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.