All tasks / Comparisons
Claude Fable 5.1 vs Qwen3.8-Max
Compared only on public benchmark results, across the 6 tasks where both are listed: Claude Fable 5.1 is a tier higher in 3 of 6 shared tasks, they share a tier in 3.
Claude Fable 5.1
Anthropic's highest-priced Claude tier, positioned for demanding reasoning and long-horizon agentic work.
- Vendor
- Anthropic
- Weights
- Closed: API and apps only
- Released
- 1 Sep 2026
- API price
- $10 in / $50 out per 1M tokens
- License
- proprietary
- Last verified
- 18 Oct 2026
Qwen3.8-Max
Alibaba's hosted Qwen3.8-Max: the API version takes text, image and video input with a 1M-token context.
- Vendor
- Alibaba (Qwen)
- Weights
- Closed: API and apps only
- Released
- 2 Aug 2026
- API price
- $2 in / $6 out per 1M tokens (Alibaba Cloud Model Studio list price quoted by The Batch (cached input $0.25/1M); OpenRouter lists the same for the qwen3.8-max-0902 snapshot. The higher-throughput 'Max Prime' SKU (2026-09-23) costs $4/$12.)
- License
- proprietary
- Last verified
- 18 Oct 2026
Task by task
| Task | Claude Fable 5.1 | Qwen3.8-Max | Higher tier |
|---|---|---|---|
| Chat & assistants Models | S1,502 on LMArena Text Arena (overall, style control) · Cloud | A1,482 on LMArena Text Arena (overall, style control) · Cloud | Claude Fable 5.1 |
| Search & research Models | S1,233 on LMArena Search Arena (style control) · Cloud | S1,230 on LMArena Search Arena (style control) · Cloud | Same tier |
| Writing Models | S1,485 on LMArena Text Arena: Creative Writing (style control) · Cloud | A1,469 on LMArena Text Arena: Creative Writing (style control) · Cloud | Claude Fable 5.1 |
| Coding Models | A1,742 on LMArena WebDev / Code Arena (overall) · Cloud | B1,674 on LMArena WebDev / Code Arena (overall) · Cloud | Claude Fable 5.1 |
| Image understanding Models | S1,286 on LMArena Vision Arena (overall, style control) · Cloud | S1,301 on LMArena Vision Arena (overall, style control) · Cloud | Same tier |
| Workflow automation Models | C59.4% on AutomationBench-AA (Artificial Analysis) · Cloud | C56.2% on AutomationBench-AA (Artificial Analysis) · Cloud | Same tier |
A tier spans a range of scores, and small gaps on a leaderboard are often within its margin of error, so only a different tier counts as ahead. How we rank.
Same benchmark, both results
| Benchmark | Claude Fable 5.1 | Qwen3.8-Max | Snapshot |
|---|---|---|---|
| Artificial Analysis Intelligence Index Composite index over Artificial Analysis' own evaluation suite, higher is better | 53 | 45 | 19 Oct 2026 |
| AutomationBench-AA (Artificial Analysis) Score: average share of each task's objectives completed across 657 business-workflow tasks in 40 simulated SaaS apps via REST APIs; a task with any guardrail (business-rule) violation scores zero, higher is better | 59.4% | 56.2% | 19 Oct 2026 |
| LMArena Search Arena (style control) Arena score (Bradley-Terry rating from pairwise human votes on search-grounded answers, style-controlled view), higher is better | 1,233 | 1,230 | 13 Oct 2026 |
| LMArena Text Arena (overall, style control) Arena score (Bradley-Terry rating from pairwise human votes, style-controlled default view), higher is better | 1,502 | 1,482 | 15 Oct 2026 |
| LMArena Text Arena: Creative Writing (style control) Arena score (Bradley-Terry rating from pairwise human votes, creative-writing prompts only, style-controlled view), higher is better | 1,485 | 1,469 | 15 Oct 2026 |
| LMArena Vision Arena (overall, style control) Arena score (Bradley-Terry rating from pairwise human votes on image + text prompts, style-controlled view), higher is better | 1,286 | 1,301 | 9 Oct 2026 |
| LMArena WebDev / Code Arena (overall) Arena score (Bradley-Terry rating from pairwise human votes on web-app generation), higher is better | 1,742 | 1,674 | 18 Oct 2026 |