Overall score
47.5
Rank #61 · A confidence
Google · stable
Google's Gemma 4 31B model tracked via the BenchLM July 2026 leaderboard for capability comparison.
Overall score
47.5
Rank #61 · A confidence
Capability
46.5
20 eligible benchmark families
Coverage
81%
Confidence A
Benchmarks scored
25
25 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| MMLU-ProRanking weighted | research | 85.2% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 84.3% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 76.9% | 2026-07-15 |
| IFBench | instruction following | 75.6% | 2026-07-15 |
| IFEval | instruction following | 75.6% | 2026-07-15 |
| BenchLM Multimodal priorRanking weighted | multimodal | 67.6% | 2026-07-15 |
| BenchLM Knowledge priorRanking weighted | research | 65.2% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 62% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 59.9415% | 2026-07-15 |
| τ-benchRanking weighted | agents | 59.9% | 2026-07-15 |
| BenchLM Reasoning priorRanking weighted | reasoning | 52.3% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 50.09% | 2026-07-15 |
| SciCodeRanking weighted | coding | 43.4% | 2026-07-15 |
| SWE-RebenchRanking weighted | coding | 41.6% | 2026-07-15 |
| ITBench-AARanking weighted | agents | 37.2881% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 36.4% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 36.3636% | 2026-07-15 |
| EnterpriseOps-Gym-AARanking weighted | agents | 28.3497% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 27.31% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 26.5% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 15.2015% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 15.0515% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 1.4286% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | -45.4167 index | 2026-07-15 |
| Harvey LAB-AARanking weighted | agents | 0% | 2026-07-15 |
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: efficiency, value. The last source check for this exact model was 2026-07-16.
Related models
Exact variants remain separate even when they share a provider or family.
Gemini 3.5 · stable
Gemini 3.1 Pro PreviewGemini 3.1 · preview
Gemini 3.1 Flash-LiteGemini 3.1 · stable