Claude Opus 5
Released 24 Jul 2026$5 input, $25 output per million tokens1.0M contextproprietaryAlso written as Claude Opus 5 (Adaptive Reasoning, Max Effort), claude-opus-5, Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
9 results on 8 of 13 boards, latest measured Sep 2026. Compare with other models
Clinical Benchmarks Index63.2Rank 1 of 1496 of 10 boardsAverage × multiplier 63.2 × 1 = 63.2This site’s own calculation. Working How it is computed
Results
Each line sits on its own board's scale. Tall tick: the board leader.
Clinical reasoning and knowledge
- HealthBench Professionallength-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 73.4%).0.598Rank 14 of 35Leader GPT-6 Astra (Anthropic run) 0.703
- 57.1Rank 6 of 8 here, 11 models on the boardLeader GPT-5.6 Sol 60.2
Documentation and coding
- 90.98Rank 4 of 105Leader Claude Opus 5.5 91.43
- 63.57Rank 1 of 103Leads this board
EHR and workflow agents
- PhysicianBenchAnthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; safety classifiers enabled57.6Rank 4 of 28 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
- 55Rank 1 of 12Leads this board
- CHI-BenchListed as erius + claude-opus-5community-submitted harness config validated by automated workspace judge54.7Rank 1 of 43 here, 45 models on the boardLeads this board
- CHI-BenchListed as claude-code + claude-opus-537.3Rank 2 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
Safety
- First, Do NOHARM (v2)v2 run on ARISE; 19 models on the board74.6Rank 6 of 17 here, 19 models on the boardLeader LiSA 2.5 86.2
Index working
The Clinical Benchmarks Index is this site's own calculation: a weighted average of the board scores times a multiplier for the boards behind it. How it is computed
- HealthBench Professional0.59859.8×0.743length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 73.4%).
- MedScribe (Vals AI)90.9891.0×0.25, near its ceilingNear its ceiling: leader 91.4, weight 0.25
- MedCode (Vals AI)63.5763.6×0.911
- MAST (Medical AI Superintelligence Test)57.157.1×0.995
- First, Do NOHARM (v2)74.674.6×0.507v2 run on ARISE; 19 models on the board
- PhysicianBench57.657.6×0.79Anthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; safety classifiers enabled
- Weighted average of 6 boards
- 63.2
- Multiplier for 6 of 10 boards
- × 1
- Index
- 63.2 × 1 = 63.2
Score: the result on the board’s own 0 to 100 scale. Dot: this model; tick: the board’s leader. Weight: how much the board counts in the weighted average; bold where the board is near its ceiling and counts for less. Each result links to its quote and page; the line under it is the setting it was measured with.
Sources
The quote, page and document for each of the 9 results
14HealthBench Professional length-adjusted 0.598
Printed as 59.8%Vendor-reported, measured Jul 2026Configuration: length-adjusted, Anthropic protocol: adaptive thinking at max effort, Claude Opus 4.8 grader, averaged over 5 trials, no tools or custom system prompt (raw 73.4%).System Card: Claude Opus 5 system card, Anthropic, 24 Jul 2026. p. 189, section 8.15.2 HealthBench Professional results; also Table 8.1.A p. 152 ('HealthBench Professional 59.8 ...')Claude Opus 5 achieved a raw score of 73.4%, which is the highest amongst all Claude models, ahead of Claude Mythos 5 at 70.3%, Claude Opus 4.8 at 60.3%, and Claude Sonnet 5 at 62.4%. After length adjustment, which penalizes verbose model responses, Claude Opus 5 achieved a score of 59.8%.
Every result from this document- Also printed in Claude Fable 5.1 and Claude Mythos 5.1 System Card: 59.8%, p. 167, Table 8.1.A, column 'Claude Opus 5'; raw 73.4% also reprinted on p. 199, sec. 8.17.2
4MedScribe (Vals AI) 90.98
Printed as 90.98%Official leaderboard, measured Sep 2026Vals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 4 of 105 (Claude Opus 5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-5"].4 | Claude Opus 5 | 90.98%±1.92 | $5/$25 | 76.56s
Every result from this document1MedCode (Vals AI) 63.57
Printed as 63.57%Official leaderboard, measured Sep 2026Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 1 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-5"].1 | Claude Opus 5 | 63.57%±1.99 | $5/$25 | 24.50s
Every result from this document6MAST (Medical AI Superintelligence Test) 57.1
Printed as 57.1%Official leaderboard, measured Aug 2026MAST: Medical AI Superintelligence Test leaderboard (General board) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast, 'Which AI can you trust for medical questions?' General tab, composite score table (8 of 11 models shown; 'Last updated August 15, 2026')6 Claude Opus 5 Anthropic 57.1%
Every result from this document6First, Do NOHARM (v2) v2 run on ARISE 74.6
Printed as 74.6%Official leaderboard, measured Aug 2026Configuration: v2 run on ARISE; 19 models on the boardMAST technical leaderboard (First Do NOHARM v2 and per-benchmark results) official leaderboard, ARISE AI Research Network, 15 Aug 2026. arise-ai.org/mast/technical, 'First Do NOHARM v2 overall metric across 19 models' ranking (Latest Flagships view), plus Model Leaderboard SAFETY column6Claude Opus 5Anthropic 74.6%
Every result from this document4PhysicianBench Anthropic harness 57.6
Printed as 57.6%Vendor-reported, measured Sep 2026Configuration: Anthropic harness; 100 tasks; pass@1; max effort; Opus 5 rubric grader; safety classifiers enabledClaude Sonnet 5.5 System Card system card, Anthropic, 28 Sep 2026. pp. 138–139, Section 8.15.3; PhysicianBench pass@1, Claude Opus 5 (max).PhysicianBench is a public benchmark of 100 physician tasks carried out in an EHR. At max effort, Claude Sonnet 5.5 passes 63.2% of attempts, well above Claude Sonnet 5 (37.4%), level with Claude Fable 5.1 (61.0%), about 6 points above Claude Opus 5 (57.6%) and about 5 points below Claude Opus 5.5 (68.4%).
Every result from this document1HealthAgentBench $3.3/task 55
Printed as 55%Official leaderboard, measured Jul 2026Configuration: $3.3/task; harness+model evaluated jointlyHealthAgentBench leaderboard official leaderboard, Microsoft Research (HealthAgentBench), 27 Jul 2026. Leaderboard table (homepage), rank 1, Success Rate column1 Claude Code (Opus 5) 55% $3.3
Every result from this document- Also printed in HealthAgentBench detailed results: 55%, Detailed results table, rank 1
1CHI-Bench community-submitted harness… 54.7
Printed as 54.7%Independent run, measured Aug 2026Configuration: community-submitted harness config validated by automated workspace judgeCHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 01, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-07-26; accessed 2026-09-30.01 | erius submitted by Michael Johnson (MJ) | claude-opus-5 | Proprietary | 54.7% | 72.0% | 36.0% | 56.0% | 2026-07-26
Every result from this document- Also printed in CHI-Bench submission manifest: erius + anthropic/claude-opus-5, submission.model; provenance.started_at / finished_at; results.overall.pass_at_1; retrieved 2026-09-30
2CHI-Bench 37.3
Printed as 37.3%Official leaderboard, measured Jul 2026CHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 03, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-07-24; accessed 2026-09-30. Linked submission provenance: run 2026-07-24T19:08:02Z to 2026-07-24T23:22:36Z; submitted_at 2026-08-12T20:20:00Z.03 | claude-code | claude-opus-5 | Proprietary | 37.3% | 20.0% | 32.0% | 60.0% | 2026-07-24
Every result from this document- Also printed in CHI-Bench submission manifest: claude-code + anthropic/claude-opus-5, submission.model; provenance.started_at / finished_at; results.overall.pass_at_1; retrieved 2026-09-30
Other Anthropic models: Claude 3.7 Sonnet, Claude Fable 5, Claude Fable 5.1, Claude Haiku 4.5, Claude Haiku 5.5, Claude Opus 4.1, Claude Opus 4.5, Claude Opus 4.6, Claude Opus 4.7, Claude Opus 4.8, Claude Opus 5.5, Claude Sonnet 4, Claude Sonnet 4.5, Claude Sonnet 4.6, Claude Sonnet 5, Claude Sonnet 5.5