Model comparison
Gemma 4 31B IT vs Llama 3.2 3B
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 28.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
MetaSummary
- They share 13 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Llama 3.2 3B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.5 to 24.7.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.09 / $0.34 for Gemma 4 31B IT.
- Gemma 4 31B IT accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 4 31B IT | Llama 3.2 3B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 43.5 | 28.9 |
| Released | 2026-04-02 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 33K | 118K |
| Input $ / M tokens | $0.09 | $0.05 |
| Output $ / M tokens | $0.34 | $0.33 |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1459 | 1098 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Llama 3.2 3B: 20.1 (#143)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1095 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1465 | 1126 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#151), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1465 | 1090 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Llama 3.2 3B: —
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1431 | 1019 |
| LMArena Chinese | 1476 | 1017 |
| LMArena Russian | 1460 | 949 |
| LMArena French | 1435 | — |
| LMArena German | — | 1056 |
| LMArena Spanish | 1444 | — |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1089 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1446 | 1100 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Gemma 4 31B IT | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1443 | 1110 |
| LMArena Creative Writing | 1415 | 1094 |
| EQ-Bench Creative Writing | 1368 | 595 |
| LMArena Multi-Turn | 1452 | 1105 |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Llama 3.2 3B?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 28.9 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Llama 3.2 3B?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Gemma 4 31B IT lists at $0.09 and $0.34.
Is Gemma 4 31B IT or Llama 3.2 3B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 131K.
How many benchmarks do Gemma 4 31B IT and Llama 3.2 3B share?
13 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Llama 3.2 3B has 18.