Model comparison
DeepSeek LLM 67B vs Palm 2
Palm 2 is the stronger model overall, scoring 30.0 to 24.9 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 30.8 to 8.7.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Palm 2 | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 24.9 | 30.0 |
| 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: 31.9 (#278), Palm 2: 29.0 (#311)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Coding | 1096 | 994 |
Reasoning Palm 2 leads
DeepSeek LLM 67B: 16.5 (#304), Palm 2: 19.1 (#271)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1005 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Palm 2 leads
DeepSeek LLM 67B: 8.7 (#324), Palm 2: 30.8 (#231)
| 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: 7.0 (#313), Palm 2: —
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.4 (#267), Palm 2: 20.9 (#295)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Non-English | 1073 | 916 |
| LMArena Chinese | 1132 | 887 |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.4 (#277), Palm 2: 51.0 (#296)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1010 |
Long Context DeepSeek LLM 67B leads
DeepSeek LLM 67B: 33.1 (#265), Palm 2: 30.8 (#285)
| Benchmark | DeepSeek LLM 67B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1092 | 1010 |
Writing & Preference DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.6 (#282), Palm 2: 25.6 (#304)
| 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 30.0 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Palm 2 better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 29.0 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.