Model comparison
DeepSeek LLM 67B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 24.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Tulu 3 (Tülu 3) 70B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Tulu 3 (Tülu 3) 70B leads 25.1 to 7.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 42.7% for Tulu 3 (Tülu 3) 70B.
Side by side
| DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 24.8 | 32.6 |
| Released | 2023-11-29 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 31.3 (#273), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1096 | 1236 |
Reasoning Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 15.9 (#300), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1220 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 8.1 (#318), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 4.4% |
| LMArena Math | 1108 | 1242 |
| MATH Level 5 | 6.4% | 42.7% |
Knowledge Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 7.1 (#308), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 24.6% | 46.3% |
Multilingual Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 29.5 (#262), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1073 | 1236 |
| LMArena Chinese | 1132 | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 55.7 (#272), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 33.1 (#260), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1092 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
DeepSeek LLM 67B: 31.8 (#277), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | DeepSeek LLM 67B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1105 | 1256 |
| LMArena Creative Writing | 1067 | 1231 |
| LMArena Multi-Turn | 1082 | 1252 |
Frequently asked questions
Is DeepSeek LLM 67B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.