Model comparison
DeepSeek Coder 1.3B vs DeepSeek LLM 67B
DeepSeek LLM 67B has enough public results to be ranked (#341); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek Coder 1.3B scores higher in 0 categories and DeepSeek LLM 67B in 1 category, but none of those gaps is larger than the uncertainty.
Side by side
| DeepSeek Coder 1.3B | DeepSeek LLM 67B | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 34.5 | 24.8 |
| Released | 2023-11-02 | 2023-11-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek Coder 1.3B: 30.7 (#282), DeepSeek LLM 67B: 31.3 (#273)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| BigCodeBench Instruct | 22.8% | — |
| LMArena Coding | — | 1096 |
| BigCodeBench Complete | 29.6% | — |
| HumanEval+ | 60.4% | — |
| MBPP+ | 54.8% | — |
Reasoning Not comparable
DeepSeek Coder 1.3B: —, DeepSeek LLM 67B: 15.9 (#300)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| Epoch Capabilities Index | 62.18 | 110.54 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1070 |
| WinoGrande | 53.3% | — |
Math Not comparable
DeepSeek Coder 1.3B: —, DeepSeek LLM 67B: 8.1 (#318)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| LMArena Math | — | 1108 |
| MATH Level 5 | — | 6.4% |
| GSM8K | 4.4% | — |
Knowledge Not comparable
DeepSeek Coder 1.3B: —, DeepSeek LLM 67B: 7.1 (#308)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
| ARC (AI2) Challenge | 25.4% | — |
| MMLU | 25.8% | — |
Multilingual Not comparable
DeepSeek Coder 1.3B: —, DeepSeek LLM 67B: 29.5 (#262)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | — | 1073 |
| LMArena Chinese | — | 1132 |
Instruction Following Not comparable
DeepSeek Coder 1.3B: —, DeepSeek LLM 67B: 55.7 (#272)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | — | 1079 |
Long Context Not comparable
DeepSeek Coder 1.3B: —, DeepSeek LLM 67B: 33.1 (#260)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | — | 1092 |
Writing & Preference Not comparable
DeepSeek Coder 1.3B: —, DeepSeek LLM 67B: 31.8 (#277)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | — | 1105 |
| LMArena Creative Writing | — | 1067 |
| LMArena Multi-Turn | — | 1082 |
Frequently asked questions
Is DeepSeek Coder 1.3B better than DeepSeek LLM 67B?
DeepSeek LLM 67B has enough public results to be ranked (#341); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 1.3B or DeepSeek LLM 67B better for coding?
They score almost the same on coding (30.7 vs 31.3); test both on your own repository before choosing.
How many benchmarks do DeepSeek Coder 1.3B and DeepSeek LLM 67B share?
1 benchmark has published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and DeepSeek LLM 67B has 15.