Model comparison
DeepSeek-V3.1-Terminus vs Gemma 3n E4b IT
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 6.3× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
DeepSeek
GoogleSummary
- They share 11 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Gemma 3n E4b 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 50.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 31.5% for Gemma 3n E4b IT.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 33K.
Side by side
| DeepSeek-V3.1-Terminus | Gemma 3n E4b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.6 | 36.7 |
| Released | 2025-09-22 | 2025-05-20 |
| Weights | Open | Open |
| Context window | 164K | 33K |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.30 | $0.06 |
| Output $ / M tokens | $1 | $0.12 |
| Results tracked | 16 | 18 |
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 3n E4b IT: 36.4 (#193)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1426 | 1269 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Gemma 3n E4b IT: 19.2 (#239)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 31.5% |
| LMArena Hard Prompts | 1427 | 1284 |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Gemma 3n E4b IT: 32.5 (#186)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1402 | 1251 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemma 3n E4b IT: 33.6 (#193)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | — | 1245 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Gemma 3n E4b IT: 43.5 (#179)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1407 | 1285 |
| LMArena Russian | 1434 | 1288 |
| LMArena Chinese | — | 1310 |
| LMArena French | — | 1330 |
| LMArena German | — | 1312 |
| LMArena Japanese | — | 1274 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1305 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Gemma 3n E4b IT: 66.3 (#205)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1406 | 1255 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Gemma 3n E4b IT: 38.8 (#185)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1426 | 1277 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Gemma 3n E4b IT: 50.3 (#181)
| Benchmark | DeepSeek-V3.1-Terminus | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1420 | 1306 |
| LMArena Creative Writing | 1404 | 1287 |
| LMArena Multi-Turn | 1411 | 1276 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemma 3n E4b IT?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 6.3× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Gemma 3n E4b IT?
Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.
Is DeepSeek-V3.1-Terminus or Gemma 3n E4b IT better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 36.4 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 33K.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 3n E4b IT share?
11 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 3n E4b IT has 18.