claude-opus-5.5-max
1,811±15
1,797CI1,826
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 2 min2 minutes ago
All sources syncing normally
- Arena · Text· 6 hours ago
- Arena · WebDev· 6 hours ago
- Arena · Vision· 6 hours ago
- Arena · Agent· 6 hours ago
- GPQA Diamond· 2 minutes ago
- SWE-bench· 2 minutes ago
- Terminal-Bench· 2 minutes ago
- ARC-AGI-2· 2 minutes ago
Filter by org:
Released:
gpt-6-astra-max
1,780±11
1,770CI1,791
claude-sonnet-5.5-xhigh
1,774±14
1,760CI1,788
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-max | anthropic | Oct 2026 | $4 / $20 | 1,811 | 1,797–1,826 | #2–11 | ||
| 2 | gpt-6-astra-max | openai | Sep 2026 | $10 / $50 | 1,780 | 1,770–1,791 | #1–18 | ||
| 3 | claude-sonnet-5.5-xhigh | anthropic | Oct 2026 | $2 / $10 | 1,774 | 1,760–1,788 | #4–26 | ||
| 4 | gpt-6.1-sol-max | openai | Oct 2026 | $2 / $10 | 1,760 | 1,746–1,774 | #1–15 | ||
| 5 | claude-fable-5.1-max | anthropic | Sep 2026 | $10 / $50 | 1,743 | 1,734–1,752 | #2–21 | ||
| 6 | claude-opus-5-max | anthropic | Sep 2026 | $5 / $25 | 1,690 | 1,684–1,696 | #5–11 | ||
| 7 | gpt-6-sol-max | openai | Oct 2026 | $2 / $10 | 1,686 | 1,675–1,697 | #7–53 | ||
| 8 | Gemini 4 Argon (High) | Oct 2026 | $2 / $10 | 1,678 | 1,663–1,694 | #1–10 | |||
| 9 | Qwen3.8-Max (0902) | alibaba | Oct 2026 | $2 / $6 | 1,674 | 1,666–1,681 | #12–40 | ||
| 10 | qwen3.8-max-0902 | alibaba | Oct 2026 | $2 / $6 | 1,673 | 1,666–1,680 | #23–155 | ||
| 11 | muse-spark-1.3-max | meta | Sep 2026 | $1.25 / $4.25 | 1,659 | 1,650–1,667 | #13–33 | ||
| 12 | kimi-k3-max | moonshot | Jun 2026 | $0.25 / $11.94 | 1,655 | 1,649–1,661 | #10–39 | ||
| 13 | muse-wonder-max | meta | Oct 2026 | — | 1,651 | 1,633–1,669 | #14–56 | ||
| 14 | grok-4.7-xhigh | xai | Oct 2026 | $2 / $6 | 1,640 | 1,630–1,650 | #21–72 | ||
| 15 | mimo-v2.6-flash | xiaomi | Sep 2026 | $0.14 / $0.28 | 1,635 | 1,625–1,645 | #19–88 | ||
| 16 | qwen3.8-flash-next | alibaba | Aug 2026 | — | 1,633 | 1,625–1,641 | #53–285 | ||
| 17 | hy4-preview | tencent | Aug 2026 | $0.83 / $2.50 | 1,632 | 1,622–1,641 | #32–136 | ||
| 18 | mimo-v2.6-pro | xiaomi | Sep 2026 | $0.43 / $0.87 | 1,625 | 1,615–1,635 | #18–64 | ||
| 19 | Claude Fable 5 (High) | anthropic | Sep 2026 | $10 / $50 | 1,625 | 1,619–1,631 | #4–20 | ||
| 20 | glm-5.3-max | zai | Aug 2026 | $0.08 / $1.40 | 1,621 | 1,613–1,629 | #18–52 | ||
| 21 | deepseek-v4.1-flash-max | deepseek | Oct 2026 | $0.15 / $0.60 | 1,619 | 1,608–1,629 | #23–31 | ||
| 22 | Grok 4.6 (High) | xai | Sep 2026 | $2 / $6 | 1,617 | 1,610–1,625 | #15–52 | ||
| 23 | gpt-5.6-sol-xhigh (codex-harness) | openai | Sep 2026 | $4 / $20 | 1,617 | 1,611–1,623 | #6–25 | ||
| 24 | glm-5.3-flash | zai | Aug 2026 | $0.05 / $0.20 | 1,606 | 1,599–1,613 | #26–60 | ||
| 25 | GLM-5.2 (Max) | zai | Jun 2026 | $0.62 / $2.42 | 1,605 | 1,598–1,611 | #9–49 | ||
| 26 | qwen3.8-27b | alibaba | Aug 2026 | $0.24 / $2.20 | 1,594 | 1,588–1,601 | #32–213 | ||
| 27 | Gemini 3.7 Flash (High) | Oct 2026 | $0.75 / $3.75 | 1,591 | 1,584–1,597 | #9–57 | |||
| 28 | Gemini 3.8 Flash (High) | Oct 2026 | $0.83 / $4.13 | 1,585 | 1,578–1,593 | #2–29 | |||
| 29 | claude-haiku-5.5-high | anthropic | Oct 2026 | $0.10 / $0.50 | 1,585 | 1,573–1,597 | #43–277 | ||
| 30 | deepseek-v4-pro-high-20260813 | deepseek | Aug 2026 | $0.66 / $1.98 | 1,582 | 1,573–1,592 | #17–54 | ||
| 31 | gpt-6-luna-max | openai | Oct 2026 | $0.10 / $0.50 | 1,582 | 1,575–1,588 | #30–85 | ||
| 32 | deepseek-v4-flash-high | deepseek | Jul 2026 | $0.15 / $0.15 | 1,582 | 1,572–1,591 | #42–184 | ||
| 33 | Step 5 Preview (High) | stepfun | Sep 2026 | $1 / $2.70 | 1,565 | 1,555–1,575 | #37–159 | ||
| 34 | claude-opus-4-7-high | anthropic | Sep 2026 | $5 / $25 | 1,558 | 1,552–1,563 | #1–18 | ||
| 35 | claude-opus-4-8-high | anthropic | Sep 2026 | $5 / $25 | 1,556 | 1,550–1,562 | #15–33 |
Showing WebDev Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.