Model comparison
DeepSeek Coder 6.7B vs Granite 3.0 2b Instruct
Granite 3.0 2b Instruct has enough public results to be ranked (#286); DeepSeek Coder 6.7B 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 6.7B scores higher in 1 category and Granite 3.0 2b Instruct in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.8 to 28.3.
- The biggest single-benchmark swing is BigCodeBench Instruct: 35.5% for DeepSeek Coder 6.7B and 20.5% for Granite 3.0 2b Instruct.
Side by side
| DeepSeek Coder 6.7B | Granite 3.0 2b Instruct | |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 37.6 | 30.8 |
| Released | 2023-11-02 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 6.7B leads
DeepSeek Coder 6.7B: 35.8 (#219), Granite 3.0 2b Instruct: 28.3 (#316)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| BigCodeBench Instruct | 35.5% | 20.5% |
| LMArena Coding | — | 1090 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Granite 3.0 2b Instruct: 20.5 (#235)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1073 |
| Epoch Capabilities Index | 89.62 | — |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Granite 3.0 2b Instruct: 32.2 (#217)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | — | 1117 |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Granite 3.0 2b Instruct: 29.0 (#241)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1064 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Granite 3.0 2b Instruct: 27.0 (#278)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | — | 1033 |
| LMArena Chinese | — | 1070 |
| LMArena Russian | — | 1045 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Granite 3.0 2b Instruct: 53.9 (#284)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1056 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Granite 3.0 2b Instruct: 32.5 (#268)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1070 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Granite 3.0 2b Instruct: 29.6 (#292)
| Benchmark | DeepSeek Coder 6.7B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | — | 1080 |
| LMArena Creative Writing | — | 1046 |
| LMArena Multi-Turn | — | 1053 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Granite 3.0 2b Instruct?
Granite 3.0 2b Instruct has enough public results to be ranked (#286); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Granite 3.0 2b Instruct better for coding?
DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.8 versus 28.3 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Granite 3.0 2b Instruct share?
1 benchmark has published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Granite 3.0 2b Instruct has 13.