Model comparison
Gemma 3 4B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 28.1 on the Noometry Index.
Last verified . 11 shared benchmarks.
Google
MicrosoftSummary
- They share 11 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and Wizardlm 70b in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 70b leads 32.2 to 16.8.
Side by side
| Gemma 3 4B | Wizardlm 70b | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 28.1 | 33.0 |
| Released | 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 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.9 (#215), Wizardlm 70b: 31.4 (#285)
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1230 | 1081 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Wizardlm 70b: —
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Wizardlm 70b leads
Gemma 3 4B: 13.2 (#335), Wizardlm 70b: 20.7 (#234)
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1079 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Wizardlm 70b leads
Gemma 3 4B: 16.8 (#292), Wizardlm 70b: 32.2 (#218)
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1239 | 1116 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#299), Wizardlm 70b: —
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.5 (#194), Wizardlm 70b: 29.6 (#265)
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1273 | 1078 |
| LMArena German | 1281 | 1083 |
| LMArena Russian | 1294 | 1155 |
| LMArena Chinese | — | 1052 |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.2 (#225), Wizardlm 70b: 56.3 (#273)
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1239 | 1093 |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.7 (#194), Wizardlm 70b: 33.3 (#263)
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1273 | 1097 |
Writing & Preference Gemma 3 4B leads
Gemma 3 4B: 42.0 (#239), Wizardlm 70b: 34.8 (#269)
| Benchmark | Gemma 3 4B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1291 | 1120 |
| LMArena Creative Writing | 1271 | 1149 |
| LMArena Multi-Turn | 1255 | 1108 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Wizardlm 70b better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 31.4 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Wizardlm 70b share?
11 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Wizardlm 70b has 12.