Model comparison
Gemini 3 Pro vs Gemma 4 31B IT
Gemini 3 Pro is the stronger model overall, scoring 54.7 to 43.2 on the Noometry Index.
Last verified . 28 shared benchmarks.
GoogleSummary
- They share 28 benchmarks with published results for both. Gemini 3 Pro scores higher in 8 categories and Gemma 4 31B IT in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Pro leads 64.3 to 37.9.
- The biggest single-benchmark swing is Chess Puzzles: 31% for Gemini 3 Pro and 5% for Gemma 4 31B IT.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Pro | Gemma 4 31B IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 54.7 | 43.2 |
| Released | 2025-11-18 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.09 |
| Output $ / M tokens | — | $0.34 |
| Results tracked | 67 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Gemini 3 Pro: 52.1 (#33), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1439 | 1364 |
| WeirdML | 69.9% | 52.3% |
| LMArena Coding | 1482 | 1459 |
| ALE-Bench | 1,177 | 925.5 |
| SWE-bench Verified | 72.9% | — |
| SWE-bench Verified (bash only) | 74.2% | — |
| SWE-bench Multilingual | 68.7% | — |
| SciCode | — | 43.4% |
| GSO | 18.6% | — |
| AlgoTune | 1.83 | — |
Agentic & Tool Use Not comparable
Gemini 3 Pro: 40.5 (#21), Gemma 4 31B IT: —
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| Terminal-Bench | 69.4% | — |
| Berkeley Function Calling Leaderboard | 72.5% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 71% | — |
| Vending-Bench 2 | 5,478 | — |
Reasoning Gemini 3 Pro leads
Gemini 3 Pro: 52.5 (#28), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 80.1% | 63.5% |
| NYT Connections (extended) | 94.4% | 70.6% |
| CritPt | 6.9% | 1.4% |
| Chess Puzzles | 31% | 5% |
| LMArena Hard Prompts | 1481 | 1448 |
| Epoch Capabilities Index | 152.96 | 142.74 |
| ARC-AGI-2 | 31.1% | — |
| SimpleBench | 76.4% | — |
| ARC-AGI-1 | 75% | — |
| EnigmaEval | 18.2% | — |
| Thematic Generalization | — | 53% |
| DTBench | — | 82.7% |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| ForecastBench | 61.2 | — |
Math Gemini 3 Pro leads
Gemini 3 Pro: 48.8 (#50), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.4% | 73.3% |
| LMArena Math | 1475 | 1464 |
| MathArena Final-Answer Competitions | 67% | — |
| ProofBench | 20% | — |
| Omni-MATH | 55.5% | — |
| FrontierMath (Feb 2025 set) | 37.6% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge Gemini 3 Pro leads
Gemini 3 Pro: 64.3 (#15), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 92.6% | 75.8% |
| Vectara Hallucination Rate | 13.6% | 7.4% |
| LMArena Expert | 1475 | 1465 |
| Humanity's Last Exam | 37.5% | — |
| SimpleQA Verified | — | 10.4% |
| MMLU-Pro | 90.3% | — |
| GPQA (HELM) | 80.3% | — |
Multimodal Gemini 3 Pro leads
Gemini 3 Pro: 56.9 (#1), Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1305 | 1278 |
| LMArena Document | 1434 | 1425 |
| GeoBench | 84% | — |
| VPCT | 91% | — |
Multilingual Gemini 3 Pro leads
Gemini 3 Pro: 57.1 (#14), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1474 | 1431 |
| LMArena Chinese | 1522 | 1478 |
| LMArena French | 1492 | 1436 |
| LMArena Russian | 1493 | 1462 |
| LMArena Spanish | 1468 | 1443 |
| LMArena German | 1517 | — |
| LMArena Japanese | 1513 | — |
| LMArena Korean | 1449 | — |
Instruction Following Too close to call
Gemini 3 Pro: 76.4 (#42), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1458 | 1433 |
| IFEval | 87.7% | — |
Long Context Too close to call
Gemini 3 Pro: 44.0 (#75), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1472 | 1446 |
| CL-bench | 15.8% | — |
Writing & Preference Gemini 3 Pro leads
Gemini 3 Pro: 66.6 (#34), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Gemini 3 Pro | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1479 | 1443 |
| LMArena Creative Writing | 1482 | 1416 |
| EQ-Bench Creative Writing | 1525 | 1368 |
| LMArena Multi-Turn | 1484 | 1452 |
| WildBench | 85.9% | — |
| EQ-Bench 4 | — | 1120 |
Frequently asked questions
Is Gemini 3 Pro better than Gemma 4 31B IT?
Gemini 3 Pro is the stronger model overall, scoring 54.7 to 43.2 on the Noometry Index.
Is Gemini 3 Pro or Gemma 4 31B IT better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 52.1 versus 41.9 in the Noometry coding category.
How many benchmarks do Gemini 3 Pro and Gemma 4 31B IT share?
28 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and Gemma 4 31B IT has 35.