Model comparison
Gemma 3n E4b IT vs Llama2 70b Steerlm Chat
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 31.2 on the Noometry Index.
Last verified . 9 shared benchmarks.
Google
NVIDIASummary
- They share 9 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 7 categories and Llama2 70b Steerlm Chat in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3n E4b IT leads 50.3 to 31.8.
Side by side
| Gemma 3n E4b IT | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 36.7 | 31.2 |
| Released | 2025-05-20 | — |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.12 | — |
| Results tracked | 18 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3n E4b IT: 36.4 (#193), Llama2 70b Steerlm Chat: 29.3 (#295)
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1269 | 1025 |
Reasoning Too close to call
Gemma 3n E4b IT: 19.2 (#239), Llama2 70b Steerlm Chat: 19.1 (#245)
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1047 |
| Kagi LLM Benchmark | 31.5% | — |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 32.5 (#186), Llama2 70b Steerlm Chat: 28.8 (#223)
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1251 | 1072 |
Knowledge Not comparable
Gemma 3n E4b IT: 33.6 (#193), Llama2 70b Steerlm Chat: —
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Expert | 1245 | — |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.5 (#179), Llama2 70b Steerlm Chat: 28.9 (#265)
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1285 | 1064 |
| LMArena Chinese | 1310 | — |
| LMArena French | 1330 | — |
| LMArena German | 1312 | — |
| LMArena Japanese | 1274 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1288 | — |
| LMArena Spanish | 1305 | — |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.3 (#205), Llama2 70b Steerlm Chat: 54.5 (#274)
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1255 | 1061 |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.8 (#185), Llama2 70b Steerlm Chat: 30.4 (#283)
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1277 | 998 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.3 (#181), Llama2 70b Steerlm Chat: 31.8 (#278)
| Benchmark | Gemma 3n E4b IT | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1306 | 1098 |
| LMArena Creative Writing | 1287 | 1091 |
| LMArena Multi-Turn | 1276 | 1058 |
Frequently asked questions
Is Gemma 3n E4b IT better than Llama2 70b Steerlm Chat?
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 31.2 on the Noometry Index.
Is Gemma 3n E4b IT or Llama2 70b Steerlm Chat better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 29.3 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Llama2 70b Steerlm Chat has 9.