Model comparison
Gemma 4 31B IT vs Llama 3-8B
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 25.5 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
MetaSummary
- They share 19 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 8.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 1.9% for Llama 3-8B.
Side by side
| Gemma 4 31B IT | Llama 3-8B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 43.5 | 25.5 |
| Released | 2026-04-02 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 34 |
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 3-8B: 31.0 (#289)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1459 | 1152 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 31.9% |
| BigCodeBench Complete | — | 36.9% |
| ALE-Bench | 925.5 | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Llama 3-8B: 14.3 (#326)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| Chess Puzzles | 5% | 0% |
| LMArena Hard Prompts | 1448 | 1133 |
| DTBench | 82.7% | 43.9% |
| Epoch Capabilities Index | 142.74 | 116.45 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Thematic Generalization | 53% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Llama 3-8B: 8.8 (#323)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 1.9% |
| LMArena Math | 1465 | 1151 |
| MATH Level 5 | — | 6.1% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#151), Llama 3-8B: 7.8 (#308)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 75.8% | 26.1% |
| LMArena Expert | 1465 | 1113 |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Llama 3-8B: —
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Llama 3-8B: 30.8 (#261)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1431 | 1098 |
| LMArena Chinese | 1476 | 1076 |
| LMArena French | 1435 | 1159 |
| LMArena Russian | 1460 | 1109 |
| LMArena Spanish | 1444 | 1173 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1004 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Llama 3-8B: 58.4 (#260)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1127 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Llama 3-8B: 34.2 (#251)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1446 | 1128 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Llama 3-8B: 37.5 (#256)
| Benchmark | Gemma 4 31B IT | Llama 3-8B |
|---|---|---|
| LMArena Text | 1443 | 1166 |
| LMArena Creative Writing | 1415 | 1150 |
| LMArena Multi-Turn | 1452 | 1152 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Llama 3-8B?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 25.5 on the Noometry Index.
Is Gemma 4 31B IT or Llama 3-8B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 31.0 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and Llama 3-8B share?
19 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Llama 3-8B has 34.