Model comparison
DeepSeek LLM 67B vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 24.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in knowledge, where Nova Premier 1.0 leads 35.8 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Nova Premier 1.0 | |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 24.9 | 38.3 |
| Released | 2023-11-29 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 10K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $12.50 |
| Results tracked | 15 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek LLM 67B: 31.9 (#278), Nova Premier 1.0: —
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| LMArena Coding | 1096 | — |
Reasoning Nova Premier 1.0 leads
DeepSeek LLM 67B: 16.5 (#304), Nova Premier 1.0: 23.0 (#185)
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| Epoch Capabilities Index | 110.5 | — |
Math Nova Premier 1.0 leads
DeepSeek LLM 67B: 8.7 (#324), Nova Premier 1.0: 33.8 (#199)
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Nova Premier 1.0 leads
DeepSeek LLM 67B: 7.0 (#313), Nova Premier 1.0: 35.8 (#180)
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), Nova Premier 1.0: —
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Nova Premier 1.0 leads
DeepSeek LLM 67B: 55.4 (#277), Nova Premier 1.0: 66.8 (#204)
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), Nova Premier 1.0: —
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Nova Premier 1.0 leads
DeepSeek LLM 67B: 31.6 (#282), Nova Premier 1.0: 51.0 (#178)
| Benchmark | DeepSeek LLM 67B | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 24.9 on the Noometry Index.
How many benchmarks do DeepSeek LLM 67B and Nova Premier 1.0 share?
0 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Nova Premier 1.0 has 6.