Model comparison
DeepSeek-V3.1-Terminus vs Gemma 2 2b IT
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 32.5 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 2 2b IT 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 36.6.
Side by side
| DeepSeek-V3.1-Terminus | Gemma 2 2b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.6 | 32.5 |
| Released | 2025-09-22 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 17 |
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 2 2b IT: 31.8 (#268)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Coding | 1426 | 1112 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Gemma 2 2b IT: 20.5 (#219)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1113 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Gemma 2 2b IT: 30.1 (#212)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Math | 1402 | 1135 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 2 2b IT: 29.3 (#229)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Expert | — | 1096 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Gemma 2 2b IT: 32.5 (#252)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Non-English | 1407 | 1121 |
| LMArena Russian | 1434 | 1118 |
| LMArena Chinese | — | 1132 |
| LMArena French | — | 1156 |
| LMArena German | — | 1114 |
| LMArena Japanese | — | 1083 |
| LMArena Korean | — | 1055 |
| LMArena Spanish | — | 1140 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Gemma 2 2b IT: 58.1 (#258)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Instruction Following | 1406 | 1118 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Gemma 2 2b IT: 34.2 (#245)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Longer Query | 1426 | 1130 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Gemma 2 2b IT: 36.6 (#258)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 2 2b IT |
|---|---|---|
| LMArena Text | 1420 | 1156 |
| LMArena Creative Writing | 1404 | 1147 |
| LMArena Multi-Turn | 1411 | 1118 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemma 2 2b IT?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 32.5 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Gemma 2 2b IT better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 31.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 2 2b IT share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 2 2b IT has 17.