Claude Fable 5.1 (Max)
1,501±39
1,463CI1,540
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 11 min11 minutes ago
All sources syncing normally
- Arena · Text· 4 hours ago
- Arena · WebDev· 4 hours ago
- Arena · Vision· 4 hours ago
- Arena · Agent· 4 hours ago
- GPQA Diamond· 11 minutes ago
- SWE-bench· 11 minutes ago
- Terminal-Bench· 11 minutes ago
- ARC-AGI-2· 11 minutes ago
Filter by org:
Released:
Claude Fable 5 (High)
1,499±23
1,477CI1,522
Claude Opus 5 (Max)
1,498±25
1,474CI1,523
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 (Max) | anthropic | Sep 2026 | $10 / $50 | 1,501 | 1,463–1,540 | #2–21 | ||
| 2 | Claude Fable 5 (High) | anthropic | Sep 2026 | $10 / $50 | 1,499 | 1,477–1,522 | #4–20 | ||
| 3 | Claude Opus 5 (Max) | anthropic | Sep 2026 | $5 / $25 | 1,498 | 1,474–1,523 | #5–11 | ||
| 4 | Muse Spark 1.3 (Max) | meta | Sep 2026 | $1.25 / $4.25 | 1,495 | 1,463–1,528 | #13–33 | ||
| 5 | Muse Spark 1.2 (xHigh) | meta | Oct 2026 | $1.25 / $4.25 | 1,481 | 1,439–1,522 | #13–112 | ||
| 6 | Gemini 3.7 Flash (High) | Oct 2026 | $0.75 / $3.75 | 1,477 | 1,449–1,505 | #9–57 | |||
| 7 | Muse Spark 1.1 | meta | Sep 2026 | $1.25 / $4.25 | 1,474 | 1,453–1,496 | #21–115 | ||
| 8 | Muse Spark | meta | Sep 2026 | — | 1,474 | 1,435–1,513 | #16–40 | ||
| 9 | glm-5.3-max | zai | Aug 2026 | $0.08 / $1.40 | 1,472 | 1,442–1,502 | #18–52 | ||
| 10 | Kimi K3 (Max) | moonshot | Jun 2026 | $0.25 / $11.94 | 1,472 | 1,449–1,494 | #10–39 | ||
| 11 | Claude Opus 4.7 | anthropic | Sep 2026 | $5 / $25 | 1,471 | 1,453–1,490 | #1–18 | ||
| 12 | deepseek-v4-pro-high-20260813 | deepseek | Aug 2026 | $0.66 / $1.98 | 1,465 | 1,425–1,506 | #17–54 | ||
| 13 | Claude Opus 4.6 | anthropic | Sep 2026 | $5 / $25 | 1,465 | 1,448–1,482 | #2–25 | ||
| 14 | qwen3.8-max | alibaba | Oct 2026 | $2 / $6 | 1,458 | 1,433–1,484 | #12–40 | ||
| 15 | gpt-5.6-sol-xhigh | openai | Sep 2026 | $4 / $20 | 1,456 | 1,433–1,478 | #6–25 | ||
| 16 | Gemini 3.1 Pro Preview | Sep 2026 | $2 / $12 | 1,454 | 1,440–1,468 | #9–36 | |||
| 17 | gpt-6-astra-max | openai | Sep 2026 | $10 / $50 | 1,453 | 1,413–1,494 | #1–18 | ||
| 18 | deepseek-v4.1-flash-max | deepseek | Oct 2026 | $0.15 / $0.60 | 1,453 | 1,414–1,492 | #23–31 | ||
| 19 | gpt-5.5-instant | openai | Sep 2026 | — | 1,451 | 1,421–1,481 | #52–114 | ||
| 20 | Gemini 3.8 Flash (High) | Oct 2026 | $0.83 / $4.13 | 1,450 | 1,425–1,475 | #2–29 | |||
| 21 | claude-opus-4-8-high | anthropic | Sep 2026 | $5 / $25 | 1,449 | 1,430–1,469 | #15–33 | ||
| 22 | Gemini 3 Pro | Jan 2026 | — | 1,448 | 1,426–1,471 | #23–90 | |||
| 23 | claude-opus-4-5-20251101 | anthropic | Nov 2025 | $5 / $25 | 1,447 | 1,429–1,466 | #20–62 | ||
| 24 | gemini-3-flash | Jan 2026 | — | 1,445 | 1,419–1,470 | #38–153 | |||
| 25 | grok-4.20-beta1 | xai | Oct 2026 | — | 1,445 | 1,417–1,473 | #46–119 | ||
| 26 | gpt-5.5-high | openai | Sep 2026 | $5 / $30 | 1,443 | 1,425–1,462 | #9–34 | ||
| 27 | glm-5.2-max | zai | Jun 2026 | $0.62 / $2.42 | 1,443 | 1,423–1,463 | #9–49 | ||
| 28 | gemini-3.5-flash-medium | Sep 2026 | $1.50 / $9 | 1,440 | 1,419–1,462 | #10–26 | |||
| 29 | glm-5.3-flash | zai | Aug 2026 | $0.05 / $0.20 | 1,440 | 1,414–1,465 | #26–60 | ||
| 30 | mimo-v2.5-pro | xiaomi | Apr 2026 | $0.43 / $0.87 | 1,436 | 1,419–1,454 | #40–129 | ||
| 31 | deepseek-v4-pro-high-preview | deepseek | Oct 2026 | — | 1,436 | 1,416–1,456 | #63–174 | ||
| 32 | claude-sonnet-5-high | anthropic | Sep 2026 | $2 / $10 | 1,434 | 1,413–1,455 | #24–58 | ||
| 33 | grok-4.20-multi-agent-beta-0309 | xai | Oct 2026 | — | 1,434 | 1,414–1,453 | #48–86 | ||
| 34 | claude-sonnet-4-6 | anthropic | Sep 2026 | $3 / $15 | 1,433 | 1,414–1,451 | #38–77 | ||
| 35 | grok-4.7-xhigh | xai | Oct 2026 | $2 / $6 | 1,433 | 1,389–1,476 | #21–72 |
Showing Korean exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.