Claude Opus 5.5 (High)
1,519±15
1,504CI1,534
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 40 min40 minutes ago
All sources syncing normally
- Arena · Text· 2 hours ago
- Arena · WebDev· 2 hours ago
- Arena · Vision· 2 hours ago
- Arena · Agent· 2 hours ago
- GPQA Diamond· 40 minutes ago
- SWE-bench· 40 minutes ago
- Terminal-Bench· 40 minutes ago
- ARC-AGI-2· 40 minutes ago
Filter by org:
Released:
Gemini 4 Argon (High)
1,516±19
1,496CI1,535
Claude Fable 5 (High)
1,501±7
1,494CI1,509
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 Opus 5.5 (High) | anthropic | Oct 2026 | $4 / $20 | 1,519 | 1,504–1,534 | #2–11 | ||
| 2 | Gemini 4 Argon (High) | Oct 2026 | $2 / $10 | 1,516 | 1,496–1,535 | #1–10 | |||
| 3 | Claude Fable 5 (High) | anthropic | Sep 2026 | $10 / $50 | 1,501 | 1,494–1,509 | #4–20 | ||
| 4 | Claude Opus 4.6 (High) | anthropic | Sep 2026 | $5 / $25 | 1,500 | 1,493–1,506 | #2–25 | ||
| 5 | Gemini 3.7 Flash (High) | Oct 2026 | $0.75 / $3.75 | 1,491 | 1,482–1,500 | #9–57 | |||
| 6 | Claude Opus 4.7 (High) | anthropic | Sep 2026 | $5 / $25 | 1,489 | 1,482–1,496 | #1–18 | ||
| 7 | Gemini 3.8 Flash (High) | Oct 2026 | $0.83 / $4.13 | 1,487 | 1,479–1,495 | #2–29 | |||
| 8 | Muse Wonder (Max) | meta | Oct 2026 | — | 1,485 | 1,462–1,508 | #14–56 | ||
| 9 | Claude Fable 5.1 (Max) | anthropic | Sep 2026 | $10 / $50 | 1,485 | 1,473–1,496 | #2–21 | ||
| 10 | Gemini 3 Pro | Jan 2026 | — | 1,485 | 1,476–1,493 | #23–90 | |||
| 11 | Gemini 3.1 Pro Preview | Sep 2026 | $2 / $12 | 1,481 | 1,476–1,486 | #9–36 | |||
| 12 | Claude Opus 5 (High) | anthropic | Sep 2026 | $5 / $25 | 1,471 | 1,464–1,478 | #5–11 | ||
| 13 | gemini-3.6-flash-high | Sep 2026 | $0.75 / $3.75 | 1,471 | 1,463–1,479 | #16–95 | |||
| 14 | claude-opus-4-5-20251101-high-32k | anthropic | Nov 2025 | — | 1,469 | 1,461–1,478 | #36–94 | ||
| 15 | claude-opus-4-8-high | anthropic | Sep 2026 | $5 / $25 | 1,469 | 1,463–1,476 | #15–33 | ||
| 16 | qwen3.8-max | alibaba | Oct 2026 | $2 / $6 | 1,469 | 1,460–1,478 | #12–40 | ||
| 17 | gpt-5.6-sol-xhigh | openai | Sep 2026 | $4 / $20 | 1,469 | 1,461–1,476 | #6–25 | ||
| 18 | gemini-3.5-flash-medium | Sep 2026 | $1.50 / $9 | 1,468 | 1,461–1,476 | #10–26 | |||
| 19 | claude-sonnet-5.5-xhigh | anthropic | Oct 2026 | $2 / $10 | 1,465 | 1,449–1,481 | #4–26 | ||
| 20 | Muse Spark | meta | Sep 2026 | — | 1,465 | 1,451–1,479 | #16–40 | ||
| 21 | grok-4.20-beta1 | xai | Oct 2026 | — | 1,463 | 1,454–1,473 | #46–119 | ||
| 22 | Kimi K3 (Max) | moonshot | Jun 2026 | $0.25 / $11.94 | 1,461 | 1,453–1,469 | #10–39 | ||
| 23 | claude-opus-4-5-20251101 | anthropic | Nov 2025 | $5 / $25 | 1,461 | 1,455–1,468 | #20–62 | ||
| 24 | Muse Spark 1.3 (Max) | meta | Sep 2026 | $1.25 / $4.25 | 1,461 | 1,451–1,472 | #13–33 | ||
| 25 | gpt-6.1-sol-max | openai | Oct 2026 | $2 / $10 | 1,458 | 1,441–1,475 | #1–15 | ||
| 26 | gemini-3-flash | Jan 2026 | — | 1,457 | 1,448–1,466 | #38–153 | |||
| 27 | gpt-5.5-instant | openai | Sep 2026 | — | 1,455 | 1,445–1,464 | #52–114 | ||
| 28 | glm-5.2-max | zai | Jun 2026 | $0.62 / $2.42 | 1,454 | 1,447–1,462 | #9–49 | ||
| 29 | claude-sonnet-4-5-20250929 | anthropic | Sep 2025 | $3 / $15 | 1,454 | 1,448–1,460 | #66–232 | ||
| 30 | glm-5.3-max | zai | Aug 2026 | $0.08 / $1 | 1,453 | 1,444–1,463 | #18–52 | ||
| 31 | grok-4.5 | xai | Sep 2026 | $2 / $6 | 1,452 | 1,444–1,459 | #29–70 | ||
| 32 | gpt-5.5-high | openai | Sep 2026 | $5 / $30 | 1,451 | 1,445–1,458 | #9–34 | ||
| 33 | gpt-6-astra-max | openai | Sep 2026 | $10 / $50 | 1,450 | 1,438–1,462 | #1–18 | ||
| 34 | claude-sonnet-4-5-20250929-high-32k | anthropic | Sep 2025 | — | 1,450 | 1,444–1,456 | #59–261 | ||
| 35 | claude-sonnet-4-6 | anthropic | Sep 2026 | $3 / $15 | 1,449 | 1,443–1,456 | #38–77 |
Showing Creative writing exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.