Model comparison
DeepSeek-V2.5 (Sep 2024) vs Gemma 3 4B
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 28.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
GoogleSummary
- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Gemma 3 4B in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V2.5 (Sep 2024) leads 34.8 to 11.8.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 28.1 |
| Released | 2024-09-06 | 2025-03-12 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 22 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemma 3 4B: 35.9 (#215)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1309 | 1230 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemma 3 4B: 20.9 (#142)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemma 3 4B: 13.2 (#335)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1253 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| Epoch Capabilities Index | — | 116.02 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemma 3 4B: 16.8 (#292)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Math | 1288 | 1239 |
| OTIS Mock AIME 2024-2025 | — | 7.5% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemma 3 4B: 11.8 (#299)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Expert | 1266 | 1223 |
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
Multilingual Too close to call
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemma 3 4B: 42.5 (#194)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1273 | 1273 |
| LMArena German | 1258 | 1281 |
| LMArena Russian | 1289 | 1294 |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemma 3 4B: 65.2 (#225)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1280 | 1239 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemma 3 4B: 38.7 (#194)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1301 | 1273 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemma 3 4B: 42.0 (#239)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1294 | 1291 |
| LMArena Creative Writing | 1285 | 1271 |
| LMArena Multi-Turn | 1297 | 1255 |
| EQ-Bench Creative Writing | — | 1068 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Gemma 3 4B?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 28.1 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Gemma 3 4B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemma 3 4B share?
12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemma 3 4B has 22.