Model comparison
Nova Premier 1.0 vs Tulu 3 (Tülu 3) 70B
Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 32.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where Nova Premier 1.0 leads 31.5 to 13.3.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Amazon | Allen Institute for AI (Ai2) |
| Noometry Index | 37.7 | 32.6 |
| Released | 2025-04-30 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 10K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $12.50 | — |
| Results tracked | 6 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nova Premier 1.0: —, Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | — | 1236 |
Reasoning Too close to call
Nova Premier 1.0: 22.3 (#182), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Kagi LLM Benchmark | 44.8% | — |
| LMArena Hard Prompts | — | 1220 |
Math Nova Premier 1.0 leads
Nova Premier 1.0: 31.5 (#194), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| Omni-MATH | 35% | — |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Nova Premier 1.0 leads
Nova Premier 1.0: 35.4 (#176), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| MMLU-Pro | 72.6% | — |
| GPQA (HELM) | 51.8% | — |
Multilingual Not comparable
Nova Premier 1.0: —, Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1246 |
Instruction Following Nova Premier 1.0 leads
Nova Premier 1.0: 66.9 (#201), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| IFEval | 80.3% | — |
| LMArena Instruction Following | — | 1233 |
Long Context Not comparable
Nova Premier 1.0: —, Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | — | 1224 |
Writing & Preference Nova Premier 1.0 leads
Nova Premier 1.0: 51.0 (#174), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Nova Premier 1.0 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | — | 1256 |
| LMArena Creative Writing | — | 1231 |
| WildBench | 78.8% | — |
| LMArena Multi-Turn | — | 1252 |
Frequently asked questions
Is Nova Premier 1.0 better than Tulu 3 (Tülu 3) 70B?
Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 32.6 on the Noometry Index.
How many benchmarks do Nova Premier 1.0 and Tulu 3 (Tülu 3) 70B share?
0 benchmarks have published results for both models. Nova Premier 1.0 has 6 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.