Claude Fable 5.1 (Max)
1,550±41
1,509CI1,591
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 49 min49 minutes ago
All sources syncing normally
- Arena · Text· 1 hour ago
- Arena · WebDev· 1 hour ago
- Arena · Vision· 1 hour ago
- Arena · Agent· 1 hour ago
- GPQA Diamond· 49 minutes ago
- SWE-bench· 49 minutes ago
- Terminal-Bench· 49 minutes ago
- ARC-AGI-2· 49 minutes ago
Filter by org:
Released:
Claude Fable 5 (High)
1,521±26
1,495CI1,546
Gemini 3.7 Flash (High)
1,512±31
1,482CI1,543
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 | 1,550 | 1,509–1,591 | #2–21 | ||
| 2 | Claude Fable 5 (High) | anthropic | Sep 2026 | $10 / $50 | 1,521 | 1,495–1,546 | #4–20 | ||
| 3 | Gemini 3.7 Flash (High) | Oct 2026 | $0.75 / $3.75 | 1,512 | 1,482–1,543 | #9–57 | |||
| 4 | gpt-5.5-high | openai | Sep 2026 | $5 / $30 | 1,504 | 1,483–1,526 | #9–34 | ||
| 5 | Claude Opus 5 (High) | anthropic | Sep 2026 | $5 / $25 | 1,504 | 1,483–1,525 | #5–11 | ||
| 6 | Gemini 3.8 Flash (High) | Oct 2026 | $0.83 / $4.13 | 1,504 | 1,478–1,529 | #2–29 | |||
| 7 | Gemini 3 Pro | Jan 2026 | — | 1,503 | 1,474–1,533 | #23–90 | |||
| 8 | Kimi K3 (Max) | moonshot | Jun 2026 | $0.25 / $11.94 | 1,503 | 1,477–1,529 | #10–39 | ||
| 9 | Claude Opus 4.6 (High) | anthropic | Sep 2026 | $5 / $25 | 1,499 | 1,478–1,520 | #2–25 | ||
| 10 | Gemini 3.1 Pro Preview | Sep 2026 | $2 / $12 | 1,496 | 1,479–1,514 | #9–36 | |||
| 11 | gpt-5.6-sol-xhigh | openai | Sep 2026 | $4 / $20 | 1,495 | 1,469–1,521 | #6–25 | ||
| 12 | Muse Spark 1.3 (Max) | meta | Sep 2026 | $1.25 / $4.25 | 1,492 | 1,455–1,529 | #13–33 | ||
| 13 | Claude Opus 4.7 (High) | anthropic | Sep 2026 | $5 / $25 | 1,489 | 1,465–1,513 | #1–18 | ||
| 14 | gemini-3-flash | Jan 2026 | — | 1,488 | 1,454–1,522 | #38–153 | |||
| 15 | qwen3.5-max-preview | alibaba | Oct 2026 | — | 1,484 | 1,440–1,528 | #33–77 | ||
| 16 | gpt-5.4-high | openai | Sep 2026 | $2.50 / $15 | 1,479 | 1,455–1,504 | #12–29 | ||
| 17 | gemini-3.5-flash-high | Sep 2026 | $1.50 / $9 | 1,479 | 1,455–1,503 | #10–26 | |||
| 18 | gemini-3.6-flash-high | Sep 2026 | $0.75 / $3.75 | 1,477 | 1,452–1,503 | #16–95 | |||
| 19 | grok-4.20-beta1 | xai | Oct 2026 | — | 1,476 | 1,436–1,516 | #46–119 | ||
| 20 | qwen3.8-max | alibaba | Oct 2026 | $2 / $6 | 1,475 | 1,446–1,503 | #12–40 | ||
| 21 | gpt-5.6-terra-xhigh | openai | Sep 2026 | $2 / $12 | 1,475 | 1,449–1,500 | #13–59 | ||
| 22 | Muse Spark 1.1 | meta | Sep 2026 | $1.25 / $4.25 | 1,467 | 1,443–1,491 | #21–115 | ||
| 23 | glm-5.3-max | zai | Aug 2026 | $0.08 / $1 | 1,464 | 1,433–1,494 | #18–52 | ||
| 24 | gpt-5.5-instant | openai | Sep 2026 | — | 1,463 | 1,426–1,500 | #52–114 | ||
| 25 | gpt-5.1-high | openai | Nov 2025 | $1.25 / $10 | 1,460 | 1,433–1,488 | #45–242 | ||
| 26 | claude-opus-4-8 | anthropic | Sep 2026 | $5 / $25 | 1,459 | 1,438–1,481 | #15–33 | ||
| 27 | deepseek-v4-pro | deepseek | Aug 2026 | $0.66 / $1.98 | 1,456 | 1,432–1,479 | #17–54 | ||
| 28 | glm-5.2-max | zai | Jun 2026 | $0.62 / $2.42 | 1,455 | 1,432–1,478 | #9–49 | ||
| 29 | gpt-6-sol-max | openai | Oct 2026 | $2 / $10 | 1,448 | 1,408–1,489 | #7–53 | ||
| 30 | gpt-5.2-chat-latest-20260210 | openai | Feb 2026 | — | 1,448 | 1,412–1,484 | #44–72 | ||
| 31 | claude-opus-4-5-20251101-high-32k | anthropic | Nov 2025 | — | 1,447 | 1,416–1,478 | #36–94 | ||
| 32 | gemini-3.5-flash-lite | Oct 2026 | $0.30 / $2.50 | 1,446 | 1,419–1,472 | #62–171 | |||
| 33 | deepseek-v4.1-flash-max | deepseek | Oct 2026 | $0.15 / $0.60 | 1,445 | 1,408–1,483 | #23–31 | ||
| 34 | claude-sonnet-5-high | anthropic | Sep 2026 | $2 / $10 | 1,445 | 1,421–1,469 | #24–58 | ||
| 35 | grok-4.5 | xai | Sep 2026 | $2 / $6 | 1,444 | 1,416–1,471 | #29–70 |
Showing Japanese exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.