Model comparison
Codellama 70b Instruct vs Gemma 3 4B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 28.1 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
GoogleSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Gemma 3 4B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 4B leads 42.5 to 24.8.
Side by side
| Codellama 70b Instruct | Gemma 3 4B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 33.7 | 28.1 |
| 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 | 7 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Gemma 3 4B: 35.9 (#215)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1230 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Gemma 3 4B: 20.9 (#142)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Gemma 3 4B: 13.2 (#335)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1253 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| Epoch Capabilities Index | — | 116.02 |
Math Not comparable
Codellama 70b Instruct: —, Gemma 3 4B: 16.8 (#292)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| LMArena Math | — | 1239 |
Knowledge Not comparable
Codellama 70b Instruct: —, Gemma 3 4B: 11.8 (#299)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| LMArena Expert | — | 1223 |
Multilingual Gemma 3 4B leads
Codellama 70b Instruct: 24.8 (#288), Gemma 3 4B: 42.5 (#194)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 992 | 1273 |
| LMArena German | — | 1281 |
| LMArena Russian | — | 1294 |
Instruction Following Gemma 3 4B leads
Codellama 70b Instruct: 51.9 (#293), Gemma 3 4B: 65.2 (#225)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1239 |
Long Context Not comparable
Codellama 70b Instruct: —, Gemma 3 4B: 38.7 (#194)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | — | 1273 |
Writing & Preference Gemma 3 4B leads
Codellama 70b Instruct: 33.4 (#277), Gemma 3 4B: 42.0 (#239)
| Benchmark | Codellama 70b Instruct | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1057 | 1291 |
| LMArena Creative Writing | — | 1271 |
| EQ-Bench Creative Writing | — | 1068 |
| LMArena Multi-Turn | — | 1255 |
Frequently asked questions
Is Codellama 70b Instruct better than Gemma 3 4B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 28.1 on the Noometry Index.
Is Codellama 70b Instruct or Gemma 3 4B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 35.9 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Gemma 3 4B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemma 3 4B has 22.