Model comparison
DeepSeek-V3.1-Terminus vs Palm 2
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
GoogleSummary
- They share 9 benchmarks with published results for both. DeepSeek-V3.1-Terminus 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-Terminus leads 61.0 to 25.6.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Palm 2 | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 43.1 | 30.0 |
| Released | 2025-09-22 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Palm 2: 29.0 (#311)
| Benchmark | DeepSeek-V3.1-Terminus | Palm 2 |
|---|---|---|
| LMArena Coding | 1426 | 994 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Palm 2: 19.1 (#271)
| Benchmark | DeepSeek-V3.1-Terminus | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1005 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Palm 2: 30.8 (#231)
| Benchmark | DeepSeek-V3.1-Terminus | Palm 2 |
|---|---|---|
| LMArena Math | 1402 | 1049 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Palm 2: 20.9 (#295)
| Benchmark | DeepSeek-V3.1-Terminus | Palm 2 |
|---|---|---|
| LMArena Non-English | 1407 | 916 |
| LMArena Chinese | — | 887 |
| LMArena Russian | 1436 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Palm 2: 51.0 (#296)
| Benchmark | DeepSeek-V3.1-Terminus | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1010 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Palm 2: 30.8 (#285)
| Benchmark | DeepSeek-V3.1-Terminus | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1421 | 1010 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Palm 2: 25.6 (#304)
| Benchmark | DeepSeek-V3.1-Terminus | Palm 2 |
|---|---|---|
| LMArena Text | 1419 | 1027 |
| LMArena Creative Writing | 1403 | 991 |
| LMArena Multi-Turn | 1411 | 994 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Palm 2?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.0 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Palm 2 better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 29.0 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Palm 2 share?
9 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Palm 2 has 10.