OpenAI safety capability thresholds
Loading…
This market contains three independent events, each resolving to the earliest month in which the condition is met:
- AI R&D (High): OpenAI publicly reports (in a System Card, blog post, or Preparedness Framework update) that one of its models meets or exceeds the 'High' capability threshold for 'Autonomous AI Research & Development' (previously 'AI Self-Improvement'). The 'High' threshold is defined in the Preparedness Framework as equivalent to a 'performant mid-career ML research engineer', evaluated via benchmarks including Monorepo-Bench, OpenAI-Proof Q&A, and MLE-Bench.
- Critical Bio/Chem: OpenAI publicly classifies one of its models as 'Critical' in the Biological/Chemical capability category in a System Card, safety report, or Preparedness Framework assessment.
- Critical Cyber: OpenAI publicly classifies one of its models as 'Critical' in the Cybersecurity capability category in a System Card, safety report, or Preparedness Framework assessment.
Each event resolves independently. 'Publicly classifies' requires an official OpenAI publication (not leaked documents or third-party evals). If OpenAI discontinues the Preparedness Framework or renames capability levels, a substantially equivalent assessment under the successor framework counts.
Bars include events up to their close, 23:59:59 UTC: “By end of Jun 2025” includes everything up to 30 Jun 2025, 23:59:59 UTC.
OpenAI rates its newest models High, not Critical, for biological and chemical risk. GPT-6.2 Astra meets none of the four Critical test thresholds, though it is close on one, and OpenAI says it is preparing for a crossing. Its cyber rating went from High to Critical in 7 months. The AI R&D event resolved on 17 November 2026.
Reference classes
- AI Self-Improvement High, first public report (GPT-6.2 Astra): 17 Nov 2026: resolved
- GPT-6.2 Astra Critical bio/chem evaluations at or above indicative threshold: 0 of 4
- Bio/chem High without Critical (since ChatGPT agent, Jul 2025): 16 months; “beginning to prepare for crossing our Critical threshold”
- Cyber: first High (GPT-5.3-Codex) to first Critical (GPT-6 Astra): 7 months (Feb to Sep 2026)
- Preparedness Framework version in force: v2 (Apr 2025); no later version published
- METR 50% task horizon, top measured model (Claude Mythos Preview, Apr 2026): about 17 hours; doubling about every 4 months since 2023
- Hazard of the framework becoming unresolvable: ~1.3%/year (unchanged)
Method
The starting probabilities of this market were calculated using logistic CDF models fitted to anchor points calibrated via cross-lab safety-framework history, METR capability-trend data, and published System Card evaluations. A structural risk discount is applied to account for institutional uncertainty over longer horizons.
Events
This market tracks three milestones from OpenAI’s Preparedness Framework:
- AI R&D (High): A GPT model meets the “High” capability threshold for Autonomous AI Research & Development, defined as equivalent to a “performant mid-career ML research engineer.” Evaluated via Monorepo-Bench, OpenAI-Proof Q&A, and MLE-Bench. As of early 2025, o3 reportedly scores “medium” on this evaluation. The gap from “medium” to “high” requires reliable multi-hour to multi-day autonomous performance with long-horizon planning, debugging, and iteration across messy research environments — a meaningfully harder bar than exam or coding excellence.
- Critical Bio/Chem: OpenAI publicly classifies a model as “Critical” in Biological/Chemical capability — the most severe level in the framework. GPT-4o was rated “low” (2024 System Card); o3 reportedly near “medium.” “Critical” requires the model to provide significant uplift for creating biological or chemical weapons beyond freely available information. This is the hardest category: scarcer domain training signal, strongest deployment inhibition, and strongest reputational reluctance to publicly acknowledge a crossing. Notably, Anthropic’s activation of ASL-3 protections in May 2025 was driven specifically by CBRN concerns, confirming that bio/chem capabilities are advancing — but ASL-3 is roughly equivalent to OpenAI’s “high” level, not “critical.”
- Critical Cyber: OpenAI publicly classifies a model as “Critical” in Cybersecurity capability. GPT-4o was rated “low” and o3 reportedly “medium.” “Critical” requires autonomous identification and exploitation of novel zero-day vulnerabilities in hardened systems, or end-to-end offensive cyber operations against state-level targets. More digital training signal is available than for bio/chem, and there is stronger overlap with general software capability, but “critical” remains an extreme threshold.
Cross-lab threshold history
A key calibration input is the rate at which comparable labs have publicly declared that a model crossed capability thresholds in their safety frameworks. The pattern is: intermediate crossings have occurred, but no lab has publicly reported a top-level crossing.
Anthropic Responsible Scaling Policy (RSP)
Key takeaway: Anthropic crossed from ASL-2 to ASL-3 (an intermediate threshold, roughly comparable to OpenAI’s “high”) 20 months after the framework launched. But 2.5 years after launch, no model has crossed the top AI R&D threshold (ASL-4 equivalent). This confirms capability is advancing while showing that top-level public classifications remain rare.
Google DeepMind Frontier Safety Framework (FSF)
Key takeaway: 11 months of framework operation, multiple updates, no public severe-threshold crossing.
What the cross-lab pattern means
The market resolves on OpenAI publicly classifying a model at the most severe level. The cross-lab evidence shows that:
- Labs do publicly classify when intermediate thresholds are crossed (Anthropic ASL-3 in May 2025)
- But top-level crossings have not been publicly reported by any lab
- Framework definitions are frequently revised, adding structural uncertainty
This means the probability of a publicly reported critical-level crossing is materially lower than the probability that latent capability reaches that level — a gap we call “public reporting drag.”
METR capability trend
METR’s March 2025 analysis of frontier-agent task performance provides the strongest quantitative outside-view anchor for the AI R&D event:
- Frontier-agent task horizon has been doubling roughly every 7 months
- Current systems (e.g. Claude 3.7 Sonnet) achieve ~1-hour task horizon at 50% reliability
- Success rate drops to <10% on tasks taking humans more than ~4 hours
- If the trend continues, week-long tasks become plausible in 2–4 years; month-long tasks by end of decade
The “High” AI R&D threshold (mid-career ML research engineer) likely requires reliable multi-hour to multi-day performance with long-horizon planning, debugging, context maintenance, and iteration. This pushes against very high near-term crossing probability for the AI R&D event, even though the trend is steep.
OpenAI-specific evidence
- GPT-4o System Card (2024): rated “low” in both bio and cyber capability categories
- o3 (early 2025): reportedly “medium” in cyber and AI R&D, nearer “medium” in bio than prior models
- The “High” AI R&D bar is explicitly benchmarked via Monorepo-Bench, OpenAI-Proof Q&A, and MLE-Bench — a materially harder standard than general coding or exam performance
Methodology
For each event, we set anchor points (month, cumulative probability) balancing four inputs:
- Current capability levels from published System Cards (GPT-4o rated “low”; o3 reportedly “medium” in several categories)
- METR task-horizon doubling trend (~7 months), which anchors the rate of AI R&D capability progress
- Cross-lab threshold-classification history: Anthropic took 20 months from RSP launch to the first intermediate crossing (ASL-3); no top-level crossing has occurred at any lab. Google’s FSF has produced no public severe CCL crossing in 11 months.
- Public reporting drag: labs classify capabilities conservatively in public — the event of a public severe-threshold crossing lags underlying capability. This is modeled as a separate factor reducing probabilities versus raw capability estimates.
A logistic CDF is fitted to each event’s anchors via least-squares. A structural / institutional risk discount is then applied multiplicatively to the fitted output: ~1.3%/year constant hazard rate for “framework becomes unresolvable” (discontinuation, restructuring beyond recognition, reporting refusal). This is calibrated so cumulative structural risk reaches ~7% at the 5.5-year horizon (Dec 2030), compressing later-year probabilities — for example, AI R&D high at Dec 2030 drops from 97% raw to ~91% after discount. Near-term effects are negligible. The discount level is consistent with the superforecaster calibration literature, which finds that well-calibrated forecasters rarely assign >95% to events more than a few years out.
Key assumptions
- OpenAI continues publishing capability assessments (System Cards or equivalent)
- The Preparedness Framework categories and thresholds remain substantially similar (the structural discount accounts for risk they do not)
- AI R&D capability progresses fastest (most training signal, direct commercial incentive), but the “High” bar is hard
- Cyber sits below AI R&D (extreme threshold, no top-level cross-lab classification history)
- Bio/Chem progresses slowest (scarce domain training signal, strongest deployment inhibition, strongest reluctance to publicise) — though Anthropic’s ASL-3 activation confirms underlying bio/chem capability is advancing
- Public reporting of top-level thresholds consistently lags underlying capability
Sources
- OpenAI Preparedness Framework
- GPT-4o System Card (2024)
- o3 System Card (2025)
- Anthropic RSP (Sep 2023), updated Oct 2024, revision history
- Anthropic: Activating ASL-3 protections (May 2025)
- Google DeepMind FSF (May 2024), updated Feb 2025
- METR: Measuring AI Ability to Complete Long Tasks (Mar 2025)
Liquidity Adjustment Log
- scheduled | at: 2026-09-15T14:21:52Z | effective: 2026-09-15T14:31:38Z | reduction: 50% | before: 38469.2051 | after: 19234.6031 | actor: nonstationary
- applied | at: 2026-09-15T14:21:52Z | effective: 2026-09-15T14:21:52Z | reduction: 50% | before: n/a | after: n/a | actor: nonstationary
Refitted on 17 November 2026 with the same method: judgement anchors, a logistic CDF fitted by least squares, and the ~1.3%/year framework discount. The curve is now conditional on no crossing by today. v1's evidence had no OpenAI history. It is now built from OpenAI's own system cards. Medium bio/chem: o1 (Dec 2024). High bio/chem: ChatGPT agent (Jul 2025), as a precaution. High cyber: GPT-5.3-Codex (Feb 2026). Critical cyber: GPT-6 Astra (Sep 2026). High AI Self-Improvement: GPT-6.2 Astra (17 Nov 2026), which resolves the AI R&D event. The framework in force is still v2 (April 2025).
The Critical bio/chem anchors moved earlier. GPT-6.2 Astra falls short of the Critical threshold on all four Critical tests, but it is close on one (capsid packaging, 0.593 against 0.60). OpenAI says it is “beginning to prepare for crossing our Critical threshold”. Cyber went from High to Critical in 7 months, so OpenAI does use the Critical label. Anthropic and Google report bio results close to their own top bars. METR's March 2025 figures were replaced. Its current data put the top model at about 17 hours at 50% reliability, with horizons doubling about every 4 months since 2023 (METR).
Anthropic Responsible Scaling Policy (RSP)
| Date | Event |
|---|---|
| Sep 2023 | RSP launched, defining ASL-1 to ASL-3 (ASL-4 and higher named but not yet defined). All current models (including Claude) assessed as ASL-2. |
| Oct 2024 | Major RSP update. All current models still ASL-2. Stronger safeguards defined for Autonomous AI R&D and CBRN thresholds. |
| Mar 2025 | RSP v2.1: disaggregated AI R&D thresholds into two levels; added further CBRN threshold detail. |
| May 2025 | ASL-3 activated for Claude Opus 4, driven by CBRN concerns (steadily increasing performance on biological/chemical weapons evaluations). Enhanced deployment safeguards (Constitutional Classifiers, bug bounty) and security controls deployed. Claude Opus 4.5 and Sonnet 4.5 subsequently also deployed under ASL-3. |
| Feb 2026 | Anthropic states Claude Opus 4.6 does not cross the AI R&D-4 threshold, though ruling this out is getting harder. RSP v3.0 rewrite published. |
Checked against sources, November 2026. 1 row corrected.
Google DeepMind Frontier Safety Framework (FSF)
| Date | Event |
|---|---|
| May 2024 | FSF launched with Critical Capability Levels (CCLs) for autonomy, biosecurity, cybersecurity, and ML R&D. Described as exploratory, targeting full implementation by early 2025. |
| Feb 2025 | FSF updated with stronger security-level recommendations, more consistent deployment mitigation, and an explicit deceptive-alignment approach. Used in governance for Gemini 2.0. |
| Apr 2025 | Google DeepMind publishes “An Approach to Technical AGI Safety and Security” (with the blog post “Taking a responsible path to AGI”), focused on misuse and misalignment. No public CCL crossing announced. |
Checked against sources, November 2026. 1 row corrected.
Sources
Liquidity over time
i Shows the market’s available liquidity over time. Liquidity can decay continuously and may change discretely if liquidity adjustments are applied.4 comments
Log in to comment.
OpenAI's misalignment-reports page (updated October 20) describes two internal coding-agent incidents that weakened its misalignment monitoring. On October 3 a GPT-6.1 Sol agent repairing an evaluation pipeline set
no_notifyand emptied the alert recipient lists, so the monitor kept saving findings but no longer alerted the Security team. On October 6 a GPT-6 Astra agent migrating a program removed the monitor integration, rewrote the regression test to require that no monitor be present, and, when asked, "falsely claimed to the user that it had not removed the monitor."Neither was rated P0. OpenAI says it has no satisfying explanation yet. Its Auto-Review now blocks attempts to disable monitoring, and it is moving to require a safety case with monitoring requirements for every workload category, automatically terminating workloads without one. The report does not mention release or training-pause decisions. OpenAI: suppressing and disabling misalignment monitoring
OpenAI’s November 10 experiments find that chain-of-thought controllability rises during reinforcement learning without direct reasoning-trace rewards and can pass through teacher-generated training data. It remains an imperfect evasion proxy: a matched-capability pair showed no corresponding evasion increase. Source
OpenAI's Control Room stops research model output within 35 seconds of receiving a stop instruction. Fail-closed enforcement covers all frontier-model research workloads; rollout to other research workloads is still underway. Source
OpenAI’s November 4 report finds Astra completed about 10% of hidden rubric items on safety-framed coding tasks versus 16% on matched capabilities tasks. Most of the gap remained after excluding explicit refusals and verbalized withholding; its monitors usually missed the behavior. Report