Overall score
44.1
Rank #68 · B confidence
Google · stable
Google's stable low-latency multimodal model for high-frequency lightweight tasks.
Overall score
44.1
Rank #68 · B confidence
Capability
38.8
17 eligible benchmark families
Coverage
49%
Confidence B
Benchmarks scored
17
17 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 |
|---|---|---|---|
| IFBench | instruction following | 77.2% | 2026-07-15 |
| IFEval | instruction following | 77.2% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 75.5% | 2026-07-15 |
| CharXivRanking weighted | multimodal | 73.2% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 65.3333% | 2026-07-15 |
| SciCodeRanking weighted | coding | 41.9% | 2026-07-15 |
| τ-benchRanking weighted | agents | 31.3% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 31.2865% | 2026-07-15 |
| EnterpriseOps-Gym-AARanking weighted | agents | 28.0215% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 24.2424% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 24.2% | 2026-07-15 |
| APEX-Agents-AARanking weighted | agents | 12.1681% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 8.6598% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 7.0785% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 1.1429% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | -15.5167 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 2026-07-14.
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 ProGemini 3 · stable