Model profile
Claude Opus 4.7
Anthropicdeveloper
2026-04-16release date
#10 / 309overall rank
29eval lineages
2discovery sources
Evidence summary
Claude Opus 4.7 has an estimated overall rank of #10; its 90% source-sensitivity interval is #6–#61. Its behavior-only rank is #15; company governance moves the combined estimate to #10. Published evidence spans 29 evals and 7 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #6 of 241); its weakest is MORU (score, #12 of 13).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗claude-opus-4-7
- OpenRouter ↗anthropic/claude-opus-4.7
- System card ↗Exact model document · Anthropic · first party
- Release source ↗direct research preview identity date
- www.anthropic.com ↗
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #44 / 328 | ↓0.4229 | Source ↗official | |
| AgentAbstainabstain | #1 / 17 | ↑79 | Source ↗official | |
| AgentAbstaincar | #1 / 17 | ↑77.6 | Source ↗official | |
| AgentAbstainpaired | #2 / 17 | ↑59.4 | Source ↗official | |
| ANIMAscore | #5 / 22 | ↑0.735 | Source ↗official | |
| Arena Factuality — Search Arena (factuality-only weighting)factuality_bt_rating | #23 / 30 | ↑1171.0 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #45 / 112 | ↑1442.0 | Source ↗official | |
| BioSecBench-Refusalbalanced_refusal_score | #3 / 10 | ↑0.4259 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #6 / 106 | ↑0.785 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #6 / 44 | ↓44.5 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #3 / 49 | ↓19.2 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #5 / 50 | ↓28.1 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #19 / 46 | ↓85.7 | Source ↗official | |
| CAIS Risk Indexmask | #24 / 52 | ↓17.1 | Source ↗official | |
| CAIS Risk Indexpolitical_manipulation | #18 / 33 | ↓48.2 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #39 / 49 | ↓21.8 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #7 / 104 | ↓2.642 | Source ↗official | |
| DystopiaBenchbasaglia_score | #4 / 50 | ↓26.03 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #5 / 50 | ↓27.5 | Source ↗official | |
| DystopiaBenchhuxley_score | #4 / 50 | ↓18.33 | Source ↗official | |
| DystopiaBenchlaguardia_score | #2 / 50 | ↓30.07 | Source ↗official | |
| DystopiaBenchorwell_score | #3 / 50 | ↓22.73 | Source ↗official | |
| DystopiaBenchpetrov_score | #4 / 50 | ↓26.77 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #64 / 241 | ↑23.51 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #9 / 241 | ↑96.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #6 / 241 | ↑99.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #50 / 239 | ↑98.55 | Source ↗official | |
| HarmVideoBenchharmful_video_safety_recognition_reasoning | #4 / 19 | ↑0.803 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #24 / 54 | ↑27.19 | Source ↗official | |
| JuICE Cultural-Error Span Detectionf1 | #4 / 10 | ↑0.4503 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #19 / 50 | ↓85.7 | Source ↗official | |
| MANTAAWMS | #1 / 7 | ↑0.579 | Source ↗official | |
| MANTAAWVS | #1 / 7 | ↑0.76 | Source ↗official | |
| MORUscore | #12 / 13 | ↑67.2 | Source ↗official | |
| ODCV-Benchaverage_severity | #1 / 12 | ↓0.0125 | Source ↗official | |
| ODCV-Benchmisalignment_rate | #1 / 12 | ↓0 | Source ↗official | |
| RefusalBenchyouden_j | #7 / 19 | ↑0.234 | Source ↗official | |
| SM-Benchadversarial | #40 / 79 | ↑81.46 | Source ↗official | |
| SM-Benchambiguous_interpretation | #19 / 79 | ↑89.29 | Source ↗official | |
| SM-Benchanti_hallucination | #20 / 79 | ↑97.38 | Source ↗official | |
| SM-Bencheq_boundaries | #57 / 79 | ↑57.87 | Source ↗official | |
| SM-Benchoverfit | #9 / 79 | ↑91.8 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #37 / 113 | ↑6.88 | Source ↗official | |
| SpeciEvalland_animal_4ns | #60 / 113 | ↓4.57 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #36 / 113 | ↓4.65 | Source ↗official | |
| SpeciEvalspeciesism | #54 / 113 | ↓1.98 | Source ↗official | |
| ToolPrivacyBenchprivate_mt_poi | #2 / 9 | ↓20.31 | Source ↗official | |
| ToolPrivacyBenchpublic_mt_poi | #4 / 9 | ↓17.83 | Source ↗official | |
| UK AISI active safety-research compromise continuationactive_compromise_continuation_rate_pct | #2 / 5 | ↓0.8 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #71 / 94 | ↑88 | Source ↗official | |
| VETO Misfired Alignmentmisfired_alignment_rate_pct | #20 / 25 | ↓10.7 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.