Model comparison
DeepSeek LLM 67B vs INTELLECT-1
DeepSeek LLM 67B has enough public results to be ranked (#347); INTELLECT-1 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeek
Hugging FaceSummary
- They share 1 benchmark with published results for both.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | INTELLECT-1 | |
|---|---|---|
| Provider | DeepSeek | Hugging Face |
| Noometry Index | 24.9 | — |
| Released | 2023-11-29 | 2024-11-29 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek LLM 67B: 31.9 (#278), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| LMArena Coding | 1096 | — |
Reasoning Not comparable
DeepSeek LLM 67B: 16.5 (#304), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| Epoch Capabilities Index | 110.5 | 100.86 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| BIG-Bench Hard | — | 34.9% |
| HellaSwag | — | 71.4% |
| WinoGrande | — | 65.8% |
Math Not comparable
DeepSeek LLM 67B: 8.7 (#324), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
| GSM8K | — | 38.6% |
Knowledge Not comparable
DeepSeek LLM 67B: 7.0 (#313), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| ARC (AI2) Challenge | — | 54.5% |
| MMLU | — | 49.9% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.6 (#282), INTELLECT-1: —
| Benchmark | DeepSeek LLM 67B | INTELLECT-1 |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than INTELLECT-1?
DeepSeek LLM 67B has enough public results to be ranked (#347); INTELLECT-1 does not yet, so treat this comparison as directional.
How many benchmarks do DeepSeek LLM 67B and INTELLECT-1 share?
1 benchmark has published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and INTELLECT-1 has 7.