Claude Fable 5.1 benchmarks
Claude Fable 5.1 is a proprietary model from Anthropic, released 1 Sep 2026. It ranks 3rd of 51 on our overall leaderboard and 1st of 42 for coding. At A$28.08 per million tokens (blended), it costs 7.8× the median model we track. It writes about 65 tokens a second, and answers start after 2.0 min on average, thinking included. It can be called from AWS Bedrock in Sydney and Melbourne and Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia.
- CONTEXT WINDOW
- 1,000,000 tokens
- MAX OUTPUT
- 128,000 tokens
- INPUT
- text, image
- WEIGHTS
- Proprietary
- RELEASED
- 1 Sep 2026
- OUTPUT SPEED
- 65 tok/s
- ANSWER STARTS AFTER
- 2.0 min (thinking included)
Claude Fable 5.1 across our rankings.
Benchmark results.
Independent test scores are for the adaptive reasoning, max effort setting. “Among tracked” ranks Claude Fable 5.1 against the 51 models on this site; LMArena ranks run across its full leaderboard.
| BENCHMARK | RESULT | AMONG TRACKED | SOURCE DETAIL |
|---|---|---|---|
| INDEPENDENT TESTS · ARTIFICIAL ANALYSIS | |||
| AA Intelligence Index | 53.4 | #2 of 51 | Adaptive reasoning, max effort |
| AA Coding Index | 81.6 | #1 of 42 | Adaptive reasoning, max effort |
| GPQA Diamond | 93.7% | #7 of 44 | Adaptive reasoning, max effort |
| Humanity’s Last Exam | 59.1% | #2 of 51 | Adaptive reasoning, max effort |
| AA-LCR | 85.3% | #4 of 51 | Adaptive reasoning, max effort |
| Terminal-Bench 2.1 | 91.4% | #1 of 42 | Adaptive reasoning, max effort |
| τ²-Bench (banking) | 47.2% | #6 of 41 | Adaptive reasoning, max effort |
| SciCode | 63.1% | #2 of 46 | Adaptive reasoning, max effort |
| BLIND HUMAN VOTES · LMARENA | |||
| LMArena Text5,783 votes · ±8 | 1499 | #5 of 42 | #5 of 402 on LMArena · 13 Sep 2026 |
| LMArena WebDev4,887 votes · ±11 | 1755 | #2 of 45 | #2 of 129 on LMArena · 22 Sep 2026 |
| LMArena Vision2,701 votes · ±12 | 1289 | #9 of 33 | #11 of 152 on LMArena · 13 Sep 2026 |
| LMArena Document1,403 votes · ±15 | 1493 | #4 of 26 | #6 of 44 on LMArena · 13 Sep 2026 |
| LMArena Agent13,320 sessions | #1 | #1 of 37 | #1 of 46 on LMArena · 15 Sep 2026 |
What Claude Fable 5.1 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$14.04 | US$10.00 |
| Output tokens | A$70.19 | US$50.00 |
| Blended (3 in : 1 out) | A$28.08 | US$20.00 |
| JOB | COST (AUD) | MEDIAN MODEL |
|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$49.14 | ≈ A$6.58 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$33.69 | ≈ A$4.74 |
| Agentic coding taskPER 10 TASKS | A$26.67 | ≈ A$3.72 |
| SETTING | INTELLIGENCE | A$ / 1M | SPEED |
|---|---|---|---|
| Adaptive reasoning, max effort | 53.4 | A$28.08 | 65 tok/s |
| Adaptive reasoning, xhigh effort | 53.2 | A$28.08 | 59 tok/s |
| Adaptive reasoning, high effort | 51.2 | A$28.08 | 49 tok/s |
| Adaptive reasoning, medium effort | 48.9 | A$28.08 | 50 tok/s |
| Adaptive reasoning, low effort | 46.8 | A$28.08 | 49 tok/s |
Running Claude Fable 5.1 in Australia.
It can be called from AWS Bedrock in Sydney and Melbourne and Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia. How the platforms compare →
| PLATFORM | AVAILABILITY | DETAIL |
|---|---|---|
| AWS Bedrock · Sydney | GLOBAL | |
| AWS Bedrock · Melbourne | GLOBAL | |
| Azure · Australia East | NOT IN AU | |
| Google Vertex AI · Sydney | GLOBAL |
Compare it with.
Claude Fable 5.1, answered.
How much does Claude Fable 5.1 cost in Australian dollars?
Claude Fable 5.1 lists at US$10.00 per million input tokens and US$50.00 per million output tokens — A$14.04 and A$70.19 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$49.14 per 1,000 replies, before any reasoning tokens.
Can I use Claude Fable 5.1 in Australia with data kept onshore?
Claude Fable 5.1 can be called from AWS Bedrock in Sydney and Melbourne and Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.
Is Claude Fable 5.1 good for coding?
It ranks 1st of 42 on our coding ranking, with an Artificial Analysis Coding Index of 81.6 and an LMArena WebDev rating of 1755 (2nd of 129).
How good is Claude Fable 5.1 at agent and automation work?
It ranks 1st of 41 on our agents ranking, completing 47.2% of τ²-Bench banking customer-service tasks and 91.4% of Terminal-Bench 2.1 tasks.
How fast is Claude Fable 5.1?
Artificial Analysis measures Claude Fable 5.1 at about 65 tok/s of output, with the answer starting after 2.0 min on average once thinking time is included (adaptive reasoning, max effort setting).
What is Claude Fable 5.1’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 85.3%.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 22 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 23 Sep 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.7123 on 22 Sep 2026 · prices exclude GST
Snapshot 23 Sep 2026 · updated weekly · How the rankings work →