BlogLLM Benchmark Scores as Published, Side by Side
Google Contextual Security Robustness: Results as Published
Every result the catalog holds for Google Contextual Security Robustness: 3 models from 1 developer, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Safety and AlignmentMaintainer Google DeepMind (internal evaluation)Data version 2026103001, as of 2026-10-30
Baseline safe behavior without an adversary, and survival under static and 15-attempt adaptive attacks in noisy multi-app tool outputs (Figure 6.4, section 6.1.2.2).
Not checked against a maintainer's page.
Contextual Security Robustness: baseline (no adversary)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Gemini 4 ArgonGoogle, released 2026-09-30 | 83% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
| Gemini 3.8 FlashGoogle, released 2026-09-02 | 63% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 47% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
Contextual Security Robustness: survival at 1 attempt (static)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Gemini 4 ArgonGoogle, released 2026-09-30 | 57% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
| Gemini 3.8 FlashGoogle, released 2026-09-02 | 63% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 47% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
Contextual Security Robustness: survival at 15 attempts (adaptive)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Gemini 4 ArgonGoogle, released 2026-09-30 | 27% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
| Gemini 3.8 FlashGoogle, released 2026-09-02 | 23% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 0% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.