Model comparison
DeepSeek-V3.1-Terminus vs Gemma 1.1 2b IT
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.3 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 1.1 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 61.0 to 25.1.
Side by side
| DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 43.1 | 29.3 |
| Released | 2025-09-22 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 16 |
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), Gemma 1.1 2b IT: 30.1 (#299)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Coding | 1426 | 1034 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 17.7% |
| MBPP+ | — | 23.3% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Gemma 1.1 2b IT: 19.1 (#270)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| 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), Gemma 1.1 2b IT: 30.8 (#232)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Math | 1402 | 1047 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 1.1 2b IT: 26.5 (#258)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Expert | — | 970 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Gemma 1.1 2b IT: 24.6 (#289)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Non-English | 1407 | 988 |
| LMArena Russian | 1436 | 990 |
| LMArena Chinese | — | 1012 |
| LMArena German | — | 944 |
| LMArena Korean | — | 899 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Gemma 1.1 2b IT: 49.9 (#299)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Instruction Following | 1404 | 992 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Gemma 1.1 2b IT: 30.6 (#286)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Longer Query | 1421 | 1003 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Gemma 1.1 2b IT: 25.1 (#306)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Text | 1419 | 1022 |
| LMArena Creative Writing | 1403 | 998 |
| LMArena Multi-Turn | 1411 | 959 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemma 1.1 2b IT?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.3 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Gemma 1.1 2b IT better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 30.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 1.1 2b IT share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 1.1 2b IT has 16.