Claude Opus 4.8
Released 28 May 2026$5 input, $25 output per million tokens1.0M contextproprietaryAlso written as claude-opus-4-8
9 results on 6 of 13 boards, latest measured Sep 2026. Compare with other models
Clinical Benchmarks Index50.3Rank 13 of 1494 of 10 boardsAverage × multiplier 61.6 × 0.816 = 50.3This 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 ProfessionalAnthropic June evaluation; length-adjusted; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt0.574Rank 18 of 35Leader GPT-6 Astra (Anthropic run) 0.703
- HealthBench Professionallength-adjusted, adaptive thinking at max effort, Claude Sonnet 4.6 grader (the grader used by the Opus 4.8 card itself); the other Claude rows on this board use the Claude Opus 4.8 grader, under which Anthropic later prints 57.4 for this model.0.558Rank 20 of 35Leader GPT-6 Astra (Anthropic run) 0.703
- MedXpertQA (MM)Qwen-run comparison in the Qwen3.8-Max launch post71.7Rank 9 of 22 here, 5 models on the boardLeader GPT-5.6 Sol 81.5
Documentation and coding
- MedScribe (Vals AI)model ID anthropic/claude-opus-4-8; temperature=1; max_output_tokens=30000; compute_effort=max85.75Rank 23 of 105Leader Claude Opus 5.5 91.43
- 53.22Rank 9 of 103Leader Claude Opus 5 63.57
EHR and workflow agents
- 36Rank 4 of 12Leader Claude Code (Opus 5) 55
- 32Rank 6 of 12Leader Claude Code (Opus 5) 55
- CHI-BenchListed as erius + claude-opus-4-837.3Rank 2 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- CHI-BenchListed as claude-code + claude-opus-4-833.3Rank 4 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
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 Professional0.57457.4×0.743Anthropic June evaluation; length-adjusted; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system prompt
- MedScribe (Vals AI)85.7585.8×0.25, near its ceilingNear its ceiling: leader 91.4, weight 0.25model ID anthropic/claude-opus-4-8; temperature=1; max_output_tokens=30000; compute_effort=max
- MedCode (Vals AI)53.2253.2×0.911
- MedXpertQA (MM)71.771.7×0.463, near its ceilingNear its ceiling: leader 81.5, weight 0.463Qwen-run comparison in the Qwen3.8-Max launch post
- Weighted average of 4 boards
- 61.6
- Multiplier for 4 of 10 boards
- × 0.816
- Index
- 61.6 × 0.816 = 50.3
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
18HealthBench Professional Anthropic June evaluation 0.574
Printed as 57.4%Vendor-reported, measured Jun 2026Configuration: Anthropic June evaluation; length-adjusted; adaptive max effort; Opus 4.8 grader; five trials; no tools or custom system promptSystem Card: Claude Sonnet 5 system card, Anthropic, 30 Jun 2026. p. 139, Figure 8.12.2.A, Claude Opus 4.8 bar (visually read printed labels).HealthBench Professional | Length-adjusted score (%) | Claude Opus 4.8 | 57.4%
Every result from this document20HealthBench Professional length-adjusted 0.558
Printed as 55.8%Vendor-reported, measured May 2026Configuration: length-adjusted, adaptive thinking at max effort, Claude Sonnet 4.6 grader (the grader used by the Opus 4.8 card itself); the other Claude rows on this board use the Claude Opus 4.8 grader, under which Anthropic later prints 57.4 for this model.System Card: Claude Opus 4.8 system card, Anthropic, 28 May 2026. p. 228, section 8.14.1 HealthBench Professional; Figure 8.14.A p. 229Claude Opus 4.8 scores 55.8%, a meaningful improvement over Claude Opus 4.7 at 51.9% and Claude Sonnet 4.6 at 41.7%.
Every result from this document- A different number in Claude Fable 5 and Claude Mythos 5 System Card: 56.9, p. 252, Table 8.1.A, column Opus 4.8
- A different number in System Card: Claude Opus 5: 57.4, p. 152, Table 8.1.A, column Opus 4.8
23MedScribe (Vals AI) claude-opus-4-8 85.75
Printed as 85.75%Official leaderboard, measured Sep 2026Configuration: model ID anthropic/claude-opus-4-8; temperature=1; max_output_tokens=30000; compute_effort=maxVals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 23 of 105 (Claude Opus 4.8), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["anthropic/claude-opus-4-8"].23 | Claude Opus 4.8 | 85.75%±1.93 | $5/$25 | 82.36s
Every result from this document9MedCode (Vals AI) 53.22
Printed as 53.22%Official leaderboard, measured Sep 2026Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 9 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["anthropic/claude-opus-4-8"].9 | Claude Opus 4.8 | 53.22%±2.17 | $5/$25 | 105.92s
Every result from this document9MedXpertQA (MM) Qwen-run comparison… 71.7
Printed as 71.7Independent runConfiguration: Qwen-run comparison in the Qwen3.8-Max launch postQwen3.8-Max: A New Bar for Coding and Cowork launch post, Alibaba, 2 Aug 2026. Full Benchmark Table, second (multimodal) table, row MedXpertQA-MM; columns Opus4.8 / Fable5 / Gemini3.1-Pro / GPT5.6-Sol / Qwen3.7-Plus / Qwen3.8-Max| MedXpertQA-MM | 71.7 | 80.0 | 80.7 | 81.5 | 71.0 | 80.4 |
Every result from this document4HealthAgentBench $3.1/task 36
Printed as 36%Official leaderboard, measured Jul 2026Configuration: $3.1/taskHealthAgentBench leaderboard official leaderboard, Microsoft Research (HealthAgentBench), 27 Jul 2026. Leaderboard table (homepage), rank 4, Success Rate column4 Copilot (Opus 4.8) 36% $3.1
Every result from this document- Also printed in HealthAgentBench detailed results: 36%, Detailed results table, rank 4
- Also printed in HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents (arXiv 2606.31179v1): 36%, p. 11, Figure 4 (pooled task success rate, ten agents)
6HealthAgentBench $4.0/task 32
Printed as 32%Official leaderboard, measured Jul 2026Configuration: $4.0/taskHealthAgentBench leaderboard official leaderboard, Microsoft Research (HealthAgentBench), 27 Jul 2026. Leaderboard table (homepage), rank 6, Success Rate column6 Claude Code (Opus 4.8) 32% $4.0
Every result from this document- Also printed in HealthAgentBench detailed results: 32%, Detailed results table, rank 6
- Also printed in HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents (arXiv 2606.31179v1): 32%, p. 11, Figure 4 (pooled task success rate, ten agents)
2CHI-Bench 37.3
Printed as 37.3%Independent run, measured Aug 2026CHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 02, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-06-05; accessed 2026-09-30.02 | erius submitted by Michael Johnson (MJ) | claude-opus-4-8 | Proprietary | 37.3% | 40.0% | 16.0% | 56.0% | 2026-06-05
Every result from this document- Also printed in CHI-Bench submission manifest: erius + anthropic/claude-opus-4-8, submission.model; provenance.started_at / finished_at; results.overall.pass_at_1; retrieved 2026-09-30
4CHI-Bench 33.3
Printed as 33.3%Official leaderboard, measured May 2026CHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 04, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-05-28; accessed 2026-09-30. Linked submission provenance: run 2026-05-28T17:19:15Z to 2026-05-28T20:48:59Z; submitted_at 2026-05-28T20:53:26Z.04 | claude-code | claude-opus-4-8 | Proprietary | 33.3% | 32.0% | 28.0% | 40.0% | 2026-05-28
Every result from this document- Also printed in CHI-Bench submission manifest: claude-code + anthropic/claude-opus-4-8, 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 5, Claude Opus 5.5, Claude Sonnet 4, Claude Sonnet 4.5, Claude Sonnet 4.6, Claude Sonnet 5, Claude Sonnet 5.5