Model comparison
DeepSeek LLM 67B vs Palm 2
Palm 2 is the stronger model overall, scoring 29.4 to 24.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
GoogleSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 5 categories and Palm 2 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Palm 2 leads 28.4 to 8.1.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Palm 2 | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.8 | 29.4 |
| Released | 2023-11-29 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.3 (#273), Palm 2: 28.5 (#306)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Coding | 1096 | 995 |
Reasoning Palm 2 leads
DeepSeek LLM 67B: 15.9 (#300), Palm 2: 18.2 (#270)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1005 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math Palm 2 leads
DeepSeek LLM 67B: 8.1 (#318), Palm 2: 28.4 (#229)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Math | 1108 | 1049 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Not comparable
DeepSeek LLM 67B: 7.1 (#308), Palm 2: —
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.5 (#262), Palm 2: 21.1 (#290)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Non-English | 1073 | 916 |
| LMArena Chinese | 1132 | 887 |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.7 (#272), Palm 2: 51.3 (#291)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1010 |
Long Context DeepSeek LLM 67B leads
DeepSeek LLM 67B: 33.1 (#260), Palm 2: 30.7 (#280)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1092 | 1010 |
Writing & Preference DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.8 (#277), Palm 2: 25.7 (#299)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Text | 1105 | 1027 |
| LMArena Creative Writing | 1067 | 991 |
| LMArena Multi-Turn | 1082 | 994 |
Frequently asked questions
Is DeepSeek LLM 67B better than Palm 2?
Palm 2 is the stronger model overall, scoring 29.4 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Palm 2 better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.3 versus 28.5 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Palm 2 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Palm 2 has 10.