AA-OmniscienceVerified
60.9%
AA-Omniscience Accuracy
Models / Anthropic
Claude Opus 5 (Adaptive Reasoning, Max Effort)
Claude Opus · Released 2026-07-24
Anthropic's July 2026 Opus line. API list $5 / $25 per 1M tokens.
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
Composite64
Context1M
Input / 1M$5.0
Output / 1M$25
Knowledge cutoffopen
Output speed54 t/s
Statussolid
Family profile
Best published score in each covered benchmark family.
80/100 avg
- Knowledge
- 61
- Reasoning
- 93
- Coding
- 74
- Agentic
- 89
- Multimodal
- 85
- Long context
- 79
6 tested benchmark families
Benchmark placements
Per-benchmark positions
Where Claude Opus 5 (Adaptive Reasoning, Max Effort) places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | Agentic | #2/ 167 | 89 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #4/ 186 | 55 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #14/ 184 | 93 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #18/ 97 | 56 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #49/ 184 | 79 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #114/ 195 | Artificial Analysis | 2026-10-12 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Claude Opus 5 (Adaptive Reasoning, Max Effort) shows up, it's highlighted.
KnowledgeClaude Opus 5 (Adaptive Reasoning, Max Effort) · 61
- 167
- 265
- 361
ReasoningClaude Opus 5 (Adaptive Reasoning, Max Effort) · 93
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingClaude Opus 5 (Adaptive Reasoning, Max Effort) · 74
- 174
- 273
- 370
AgenticClaude Opus 5 (Adaptive Reasoning, Max Effort) · 89
- 191
- 289
- 389
MultimodalClaude Opus 5 (Adaptive Reasoning, Max Effort) · 85
- 186
- 285
- 384
Long contextClaude Opus 5 (Adaptive Reasoning, Max Effort) · 79
- 189
- 286
- 385
Newest receipts
11 recentLast 120 days
Benchmark rows added to the public ledger for Claude Opus 5 (Adaptive Reasoning, Max Effort) in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 54 t/s | Artificial Analysis | 4 |
| AA-LCR | Long context | 79.33% | Artificial Analysis | 18 |
| GPQA Diamond | Reasoning | 93.2% | Artificial Analysis | 18 |
| Humanity's Last Exam | Reasoning | 54.9% | Artificial Analysis | 18 |
| SciCode | Coding | 56.4% | Artificial Analysis | 18 |
| Terminal-Bench | Agentic | 89.14% | Artificial Analysis | 18 |
| CritPt | Reasoning | 29.1% | Artificial Analysis — CritPt | 45 |
| AA-Omniscience | Knowledge | 60.9% | Artificial Analysis — AA-Omniscience | 45 |
| MMMU-Pro | Multimodal | 84.7% | Artificial Analysis — MMMU-Pro | 45 |
| Terminal-Bench-Science | Agentic | 30% | Terminal-Bench-Science 0.1 announcement | 50 |
| DeepSWE | Coding | 74% | DeepSWE leaderboard | 73 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where Claude Opus 5 (Adaptive Reasoning, Max Effort) sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for Claude Opus 5 (Adaptive Reasoning, Max Effort). Scores link to the original source; gaps mean no public row exists yet.
11 of 13 catalog benchmarks have a sourced row for Claude Opus 5 (Adaptive Reasoning, Max Effort).
Knowledge
Reasoning
CritPtVerified
29.1%
CritPt composite (AA run)
GPQA DiamondVerified
93.2%
GPQA Diamond (AA run)
Humanity's Last ExamVerified
54.9%
HLE (AA run)
Coding
Agentic
Terminal-BenchVerified
89.14%
Terminal-Bench v2.1 (AA run)
Terminal-Bench-ScienceVerified
30%
TB-Science 0.1 resolution (Claude Code)
Multimodal
MMMU-ProVerified
84.7%
MMMU-Pro (AA run)
Long context
AA-LCRVerified
79.33%
AA-LCR (AA run)
Performance
AA output speedVerified
54 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Claude Opus 5.5 is the current Opus line. This list price is unchanged.
Sources
Where the numbers come from
- Artificial Analysis models index· checked 2026-09-10
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is Claude Opus 5 (Adaptive Reasoning, Max Effort)?
Claude Opus 5 (Adaptive Reasoning, Max Effort) is a Anthropic model: Anthropic's July 2026 Opus line. API list $5 / $25 per 1M tokens.
What is Claude Opus 5 (Adaptive Reasoning, Max Effort) for?
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
What does Claude Opus 5 (Adaptive Reasoning, Max Effort) cost?
Claude Opus 5 (Adaptive Reasoning, Max Effort) lists $5.0 input and $25 output per 1M tokens. Pricing last checked 2026-09-05.
How large is the Claude Opus 5 (Adaptive Reasoning, Max Effort) context window?
Claude Opus 5 (Adaptive Reasoning, Max Effort) publishes a 1M token context window.
What is the VerdictPal status of Claude Opus 5 (Adaptive Reasoning, Max Effort)?
Claude Opus 5 (Adaptive Reasoning, Max Effort) carries Solid status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.