BlogLLM Benchmark Scores as Published, Side by Side
Shade indirect prompt injection (Gray Swan): Results as Published
Every result the catalog holds for Shade indirect prompt injection (Gray Swan): 6 models from 1 developer, read from 2 pages. 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 Gray Swan (Shade adaptive attacker)Introduced 2026Data version 2026103001, as of 2026-10-30
Adaptive red-teaming tool that iteratively improves attacks on indirect prompt injection in coding and computer-use environments; attack success rate.
Not checked against a maintainer's page.
Shade coding attack success rate (attempt level)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 0.08% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, no safeguards: H5.5 6/40, Sonnet 5.5 16/40, Opus 5.5 37/40, Fable 5.1 39/40, Haiku 4.5 40/40 |
| 0% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, with probes: H5.5 0/40, Sonnet 5.5 13/40, Opus 5.5 36/40, Fable 5.1 35/40, Haiku 4.5 40/40 | |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 2.63% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Setup as reported: Shade attacker, 200 attempts per scenario, 40 scenarios; with prompt injection probes enabled; scenarios with success 13/40 |
| 3.01% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 40 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 16/40 | |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 11.13% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, with probes: H5.5 0/40, Sonnet 5.5 13/40, Opus 5.5 36/40, Fable 5.1 35/40, Haiku 4.5 40/40 |
| 54.61% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, no safeguards: H5.5 6/40, Sonnet 5.5 16/40, Opus 5.5 37/40, Fable 5.1 39/40, Haiku 4.5 40/40 | |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 8.7% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, with probes: H5.5 0/40, Sonnet 5.5 13/40, Opus 5.5 36/40, Fable 5.1 35/40, Haiku 4.5 40/40 |
| 51.93% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, no safeguards: H5.5 6/40, Sonnet 5.5 16/40, Opus 5.5 37/40, Fable 5.1 39/40, Haiku 4.5 40/40 | |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 37.51% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 40 scenarios; with prompt injection probes enabled; scenarios with success 40/40 |
| 15.76% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 40 scenarios; with prompt injection probes enabled; scenarios with success 35/40 | |
| 19.47% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 40 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 36/40 | |
| 40.3% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 40 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 40/40 | |
| Claude Haiku 4.5Anthropic, released 2025-10-15 | 30.43% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, with probes: H5.5 0/40, Sonnet 5.5 13/40, Opus 5.5 36/40, Fable 5.1 35/40, Haiku 4.5 40/40 |
| 58.4% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), coding, no safeguards: H5.5 6/40, Sonnet 5.5 16/40, Opus 5.5 37/40, Fable 5.1 39/40, Haiku 4.5 40/40 |
Shade computer use attack success rate (attempt level)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 0.07% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, no safeguards: 1/14 for Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1; 13/14 for Haiku 4.5 |
| 0.07% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, with probes: 1/14 for Haiku 5.5, Sonnet 5.5 and Fable 5.1; 1/14 for Opus 5.5; 10/14 for Haiku 4.5 | |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 0.07% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; with prompt injection probes; scenarios with success 1/14 |
| 0.07% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 1/14 | |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 0.07% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, no safeguards: 1/14 for Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1; 13/14 for Haiku 4.5 |
| 0.04% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, with probes: 1/14 for Haiku 5.5, Sonnet 5.5 and Fable 5.1; 1/14 for Opus 5.5; 10/14 for Haiku 4.5 | |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 0.07% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, with probes: 1/14 for Haiku 5.5, Sonnet 5.5 and Fable 5.1; 1/14 for Opus 5.5; 10/14 for Haiku 4.5 |
| 0.07% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, no safeguards: 1/14 for Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1; 13/14 for Haiku 4.5 | |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 1.46% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; with prompt injection probes; scenarios with success 4/14; Model setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; with prompt injection probes; scenarios with success 4/14 | With thinking |
| 2.25% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 4/14; Model setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 4/14 | With thinking | |
| 1.04% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; with prompt injection probes; scenarios with success 4/14; Model setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; with prompt injection probes; scenarios with success 4/14 | Without thinking | |
| 4.86% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 7/14; Model setup as reported: Shade attacker, 200 attempts per scenario, 14 scenarios; attempt-level rate over valid responses; without safeguards; scenarios with success 7/14 | Without thinking | |
| Claude Haiku 4.5Anthropic, released 2025-10-15 | 18.89% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, no safeguards: 1/14 for Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1; 13/14 for Haiku 4.5 |
| 10.46% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | Setup as reported: Shade indirect prompt injection attack success (scenario counts as printed in the card), computer use GUI, with probes: 1/14 for Haiku 5.5, Sonnet 5.5 and Fable 5.1; 1/14 for Opus 5.5; 10/14 for Haiku 4.5 |
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.