Model comparison
DeepSeek-V3.1-Terminus vs Gemma 2B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.1 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
GoogleSummary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Gemma 2B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 24.1.
Side by side
| DeepSeek-V3.1-Terminus | Gemma 2B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.6 | 29.1 |
| Released | 2025-09-22 | 2024-02-21 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 23 |
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: 41.5 (#114), Gemma 2B: 28.9 (#300)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| LMArena Coding | 1426 | 1010 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Gemma 2B: 17.9 (#275)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1427 | 989 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 93.57 |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Gemma 2B: 27.6 (#237)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| LMArena Math | 1402 | 1009 |
| GSM8K | — | 17.7% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 2B: —
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Gemma 2B: 23.1 (#289)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1407 | 958 |
| LMArena Russian | 1434 | 937 |
| LMArena Chinese | — | 986 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Gemma 2B: 48.8 (#297)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1406 | 971 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Gemma 2B: 29.9 (#286)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1426 | 981 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Gemma 2B: 24.1 (#303)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2B |
|---|---|---|
| LMArena Text | 1420 | 1002 |
| LMArena Creative Writing | 1404 | 986 |
| LMArena Multi-Turn | 1411 | 945 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemma 2B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.1 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Gemma 2B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 28.9 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 2B share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 2B has 23.