Model comparison
DeepSeek-V2.5 (Sep 2024) vs Gemma 3n E4b IT
DeepSeek-V2.5 (Sep 2024) and Gemma 3n E4b IT score almost the same on the Noometry Index (37.6 vs 37.3), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeek
GoogleSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 5 categories and Gemma 3n E4b IT in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V2.5 (Sep 2024) leads 25.6 to 19.9.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 37.3 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemma 3n E4b IT: 37.0 (#198)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1309 | 1268 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemma 3n E4b IT: 19.9 (#247)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1284 |
| Kagi LLM Benchmark | — | 31.5% |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemma 3n E4b IT: 35.1 (#188)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1288 | 1251 |
Knowledge Too close to call
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemma 3n E4b IT: 34.2 (#198)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | 1266 | 1246 |
Multilingual Too close to call
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemma 3n E4b IT: 43.4 (#183)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1273 | 1285 |
| LMArena Chinese | 1318 | 1309 |
| LMArena French | 1289 | 1330 |
| LMArena German | 1258 | 1311 |
| LMArena Japanese | 1228 | 1272 |
| LMArena Korean | 1209 | 1259 |
| LMArena Russian | 1289 | 1288 |
| LMArena Spanish | 1248 | 1305 |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemma 3n E4b IT: 66.1 (#210)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1280 | 1255 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemma 3n E4b IT: 38.7 (#191)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1301 | 1276 |
Writing & Preference Too close to call
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemma 3n E4b IT: 50.1 (#186)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1294 | 1306 |
| LMArena Creative Writing | 1285 | 1287 |
| LMArena Multi-Turn | 1297 | 1276 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Gemma 3n E4b IT?
DeepSeek-V2.5 (Sep 2024) and Gemma 3n E4b IT score almost the same on the Noometry Index (37.6 vs 37.3), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or Gemma 3n E4b IT better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemma 3n E4b IT share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemma 3n E4b IT has 18.