Claude Opus 4.8 benchmarks
Claude Opus 4.8 is a proprietary model from Anthropic, released 28 May 2026. It ranks 21st of 54 on our overall leaderboard and 17th of 54 for reasoning. At A$14.39 per million tokens (blended), it costs 3.3× the median model we track. It can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne.
- CONTEXT WINDOW
- 1,000,000 tokens
- MAX OUTPUT
- 128,000 tokens
- INPUT
- text, image
- WEIGHTS
- Proprietary
- RELEASED
- 28 May 2026
Claude Opus 4.8 across our rankings.
Benchmark results.
Independent test scores are for the adaptive reasoning, max effort setting. “Among tracked” ranks Claude Opus 4.8 against the 54 models on this site; LMArena ranks run across its full leaderboard.
| BENCHMARK | RESULT | AMONG TRACKED | SOURCE DETAIL |
|---|---|---|---|
| INDEPENDENT TESTS · ARTIFICIAL ANALYSIS | |||
| AA Intelligence Index | 41.8 | #20 of 54 | Adaptive reasoning, max effort |
| AA Coding Index | 74.3 | #15 of 42 | Adaptive reasoning, max effort |
| GPQA Diamond | 92.0% | #22 of 44 | Adaptive reasoning, max effort |
| Humanity’s Last Exam | 48.7% | #11 of 54 | Adaptive reasoning, max effort |
| AA-LCR | 77.7% | #46 of 54 | Adaptive reasoning, max effort |
| Terminal-Bench 2.1 | 84.6% | #12 of 42 | Adaptive reasoning, max effort |
| τ²-Bench (banking) | 34.2% | #26 of 41 | Adaptive reasoning, max effort |
| SciCode | 54.4% | #26 of 49 | Adaptive reasoning, max effort |
| BLIND HUMAN VOTES · LMARENA | |||
| LMArena Text63,577 votes · ±4 | 1481 | #19 of 49 | #23 of 410 on LMArena · 30 Sep 2026 |
| LMArena WebDev18,685 votes · ±6 | 1556 | #29 of 52 | #35 of 137 on LMArena · 30 Sep 2026 |
| LMArena Vision18,020 votes · ±7 | 1287 | #13 of 36 | #16 of 156 on LMArena · 28 Sep 2026 |
| LMArena Document11,551 votes · ±7 | 1486 | #7 of 26 | #9 of 44 on LMArena · 13 Sep 2026 |
| LMArena Search70,998 votes · ±6 | 1195 | #11 of 12 | #13 of 34 on LMArena · 24 Aug 2026 |
| LMArena Agent40,210 sessions | #10 | #9 of 42 | #10 of 46 on LMArena · 30 Sep 2026 |
What Claude Opus 4.8 costs in Australian dollars.
List prices converted at the snapshot’s RBA rate, excluding GST. Reasoning models are billed for their thinking as output tokens, so heavier settings cost more than the job estimates show.
| PER MILLION TOKENS | AUD | USD LIST |
|---|---|---|
| Input tokens | A$7.20 | US$5.00 |
| Output tokens | A$35.98 | US$25.00 |
| Blended (3 in : 1 out) | A$14.39 | US$10.00 |
| JOB | COST (AUD) | MEDIAN MODEL |
|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$25.18 | ≈ A$8.20 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$17.27 | ≈ A$5.35 |
| Agentic coding taskPER 10 TASKS | A$13.67 | ≈ A$4.27 |
Running Claude Opus 4.8 in Australia.
It can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne. How the platforms compare →
| PLATFORM | AVAILABILITY | DETAIL |
|---|---|---|
| AWS Bedrock · Sydney | AU ROUTING | |
| AWS Bedrock · Melbourne | IN REGION | In-region through the bedrock-mantle endpoint (Anthropic Messages API); the standard runtime endpoint uses the au. profile. Provider docs, checked 23 Sep 2026 |
| Azure · Australia East | NOT IN AU | |
| Google Vertex AI · Sydney | GLOBAL |
Compare it with.
Claude Opus 4.8, answered.
How much does Claude Opus 4.8 cost in Australian dollars?
Claude Opus 4.8 lists at US$5.00 per million input tokens and US$25.00 per million output tokens — A$7.20 and A$35.98 at A$1 = US$0.6949 (RBA, 1 Oct 2026), excluding GST. A typical customer support reply works out at about A$25.18 per 1,000 replies, before any reasoning tokens.
Can I use Claude Opus 4.8 in Australia with data kept onshore?
Claude Opus 4.8 can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.
Is Claude Opus 4.8 good for coding?
It ranks 15th of 42 on our coding ranking, with an Artificial Analysis Coding Index of 74.3 and an LMArena WebDev rating of 1556 (35th of 137). The current leader is Claude Fable 5.1.
How good is Claude Opus 4.8 at agent and automation work?
It ranks 18th of 41 on our agents ranking, completing 34.2% of τ²-Bench banking customer-service tasks and 84.6% of Terminal-Bench 2.1 tasks.
What is Claude Opus 4.8’s context window?
Anthropic documents a context window of 1,000,000 tokens (1M), with up to 128,000 output tokens. On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 77.7%.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 30 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 1 Oct 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.6949 on 1 Oct 2026 · prices exclude GST
Snapshot 2 Oct 2026 · updated weekly · How the rankings work →