# FailureSensorIQ leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/external-failure-sensor-iq

Every model the catalog carries a published FailureSensorIQ value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Multiple-choice accuracy |
| Tasks | Multiple-choice questions on sensors and failure modes for 10 industrial assets |
| Difficulty | Industrial maintenance and reliability knowledge |
| Published by | [BenchLM](https://benchlm.ai/benchmarks/failuresensoriq) |

IBM Research's FailureSensorIQ asks which sensors reveal which equipment failures across 10 kinds of industrial asset. It is the first published part of AssetOpsBench.

## FailureSensorIQ ranking

22 models with a published FailureSensorIQ value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Multiple-choice accuracy | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 69.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 69.1 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 69.0 | Observed 2026-11-21 · source benchlm:models |
| 4 | [o3](https://modelscale.dev/models/o3) | OpenAI | 67.6 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 67.4 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | 67.0 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 66.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Gemini 2.5 Flash](https://modelscale.dev/models/gemini-2-5-flash) | Google | 65.5 | Observed 2026-11-21 · source benchlm:models |
| 9 | [o4-mini](https://modelscale.dev/models/o4-mini) | OpenAI | 64.8 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Grok 4.1 Fast (Reasoning)](https://modelscale.dev/models/grok-4-1-fast-reasoning) | xAI | 64.6 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Sonnet 4.5](https://modelscale.dev/models/claude-sonnet-4-5) | Anthropic | 64.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Grok 4 Fast (Reasoning)](https://modelscale.dev/models/grok-4-fast-reasoning) | xAI | 64.1 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 62.9 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Claude Haiku 4.5](https://modelscale.dev/models/claude-haiku-4-5) | Anthropic | 61.8 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Qwen3 235B 2507](https://modelscale.dev/models/qwen3-235b-2507) | Alibaba | 60.8 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Claude 3.5 Sonnet](https://modelscale.dev/models/claude-3-5-sonnet) | Anthropic | 58.6 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude 3.5 Haiku](https://modelscale.dev/models/claude-3-5-haiku) | Anthropic | 57.6 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Gemini 2.0 Flash](https://modelscale.dev/models/gemini-2-0-flash) | Google | 55.8 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-OSS 120B](https://modelscale.dev/models/gpt-oss-120b) | OpenAI | 50.5 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Mistral Small 3.1](https://modelscale.dev/models/mistral-small-3-1) | Mistral | 47.9 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GPT-OSS 20B](https://modelscale.dev/models/gpt-oss-20b) | OpenAI | 43.5 | Observed 2026-11-21 · source benchlm:models |
| 22 | [DeepSeek-R1-0528](https://modelscale.dev/models/deepseek-r1-0528) | DeepSeek | 29.1 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
