Model comparison
DeepSeek-V3.1-Terminus vs Tulu 3 (Tülu 3) 70B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 33.0 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 38.5 to 14.2.
Side by side
| DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 43.1 | 33.0 |
| Released | 2025-09-22 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1426 | 1235 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1220 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1402 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1407 | 1236 |
| LMArena Russian | 1436 | 1246 |
| LMArena Chinese | — | 1249 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1233 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1421 | 1224 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | DeepSeek-V3.1-Terminus | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1419 | 1256 |
| LMArena Creative Writing | 1403 | 1231 |
| LMArena Multi-Turn | 1411 | 1252 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Tulu 3 (Tülu 3) 70B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 33.0 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Tulu 3 (Tülu 3) 70B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 36.0 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Tulu 3 (Tülu 3) 70B share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.