Model comparison
DeepSeek-V3.1 vs Palm 2
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
GoogleSummary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Palm 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 25.7.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Palm 2 | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.2 | 29.4 |
| Released | 2025-08-21 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 39.8 (#140), Palm 2: 28.5 (#306)
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| LMArena Coding | 1417 | 995 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), Palm 2: 18.2 (#270)
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1005 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.1 (#125), Palm 2: 28.4 (#229)
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| LMArena Math | 1420 | 1049 |
Knowledge Not comparable
DeepSeek-V3.1: 43.0 (#86), Palm 2: —
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1403 | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.8 (#100), Palm 2: 21.1 (#290)
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| LMArena Non-English | 1400 | 916 |
| LMArena Chinese | 1470 | 887 |
| LMArena French | 1447 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1429 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 74.1 (#105), Palm 2: 51.3 (#291)
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1010 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#227), Palm 2: 30.7 (#280)
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1422 | 1010 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.5 (#93), Palm 2: 25.7 (#299)
| Benchmark | DeepSeek-V3.1 | Palm 2 |
|---|---|---|
| LMArena Text | 1420 | 1027 |
| LMArena Creative Writing | 1401 | 991 |
| LMArena Multi-Turn | 1408 | 994 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Palm 2?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.4 on the Noometry Index.
Is DeepSeek-V3.1 or Palm 2 better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 28.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Palm 2 share?
10 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Palm 2 has 10.