Model comparison
DeepSeek Coder 6.7B vs Palm 2
Palm 2 has enough public results to be ranked (#298); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
GoogleSummary
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.8 to 29.0.
- DeepSeek Coder 6.7B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek Coder 6.7B | Palm 2 | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 30.0 |
| Released | 2023-11-02 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 10 |
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), Palm 2: 29.0 (#311)
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 994 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Palm 2: 19.1 (#271)
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | — | 1005 |
| Epoch Capabilities Index | 89.62 | — |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Palm 2: 30.8 (#231)
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| LMArena Math | — | 1049 |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Palm 2: —
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Palm 2: 20.9 (#295)
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| LMArena Non-English | — | 916 |
| LMArena Chinese | — | 887 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Palm 2: 51.0 (#296)
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | — | 1010 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Palm 2: 30.8 (#285)
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| LMArena Longer Query | — | 1010 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Palm 2: 25.6 (#304)
| Benchmark | DeepSeek Coder 6.7B | Palm 2 |
|---|---|---|
| LMArena Text | — | 1027 |
| LMArena Creative Writing | — | 991 |
| LMArena Multi-Turn | — | 994 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Palm 2?
Palm 2 has enough public results to be ranked (#298); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Palm 2 better for coding?
DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.8 versus 29.0 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Palm 2 share?
0 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Palm 2 has 10.