Model comparison
Sonar vs Tulu 3 (Tülu 3) 70B
Sonar is the stronger model overall, scoring 38.5 to 33.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Perplexity
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where Sonar leads 33.7 to 14.2.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Sonar | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Perplexity | Allen Institute for AI (Ai2) |
| Noometry Index | 38.5 | 33.0 |
| Released | 2024-01-01 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 7 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Sonar: 35.7 (#221), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LiveBench Coding | 35.1% | — |
| LMArena Coding | — | 1235 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Sonar: 21.1 (#227), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LiveBench Reasoning | 46.3% | — |
| LMArena Hard Prompts | — | 1220 |
| LiveBench Data Analysis | 37.9% | — |
| LiveBench | 46.9% | — |
Math Sonar leads
Sonar: 33.7 (#200), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LiveBench Math | 41.6% | — |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Not comparable
Sonar: —, Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
Multilingual Not comparable
Sonar: —, Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Sonar leads
Sonar: 71.4 (#150), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LiveBench Instruction Following | 76.2% | — |
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
Sonar: —, Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Sonar leads
Sonar: 52.6 (#167), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Sonar | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| LMArena Multi-Turn | — | 1252 |
| LiveBench Language | 44.1% | — |
Frequently asked questions
Is Sonar better than Tulu 3 (Tülu 3) 70B?
Sonar is the stronger model overall, scoring 38.5 to 33.0 on the Noometry Index.
Is Sonar or Tulu 3 (Tülu 3) 70B better for coding?
They score almost the same on coding (35.7 vs 36.0); test both on your own repository before choosing.
How many benchmarks do Sonar and Tulu 3 (Tülu 3) 70B share?
0 benchmarks have published results for both models. Sonar has 7 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.