Gemini 4 Argon (High)
1,552±23
1,529CI1,575
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 24 min24 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· 24 minutes ago
- SWE-bench· 24 minutes ago
- Terminal-Bench· 24 minutes ago
- ARC-AGI-2· 24 minutes ago
Filter by org:
Released:
Muse Wonder (Max)
1,529±28
1,501CI1,558
Claude Fable 5 (High)
1,518±8
1,510CI1,526
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 | Gemini 4 Argon (High) | Oct 2026 | $2 / $10 | 1,552 | 1,529–1,575 | #1–10 | |||
| 2 | Muse Wonder (Max) | meta | Oct 2026 | — | 1,529 | 1,501–1,558 | #14–56 | ||
| 3 | Claude Fable 5 (High) | anthropic | Sep 2026 | $10 / $50 | 1,518 | 1,510–1,526 | #4–21 | ||
| 4 | Claude Opus 4.6 (High) | anthropic | Sep 2026 | $5 / $25 | 1,517 | 1,511–1,523 | #2–25 | ||
| 5 | Claude Opus 4.7 (High) | anthropic | Sep 2026 | $5 / $25 | 1,516 | 1,509–1,523 | #1–18 | ||
| 6 | Muse Spark 1.2 (xHigh) | meta | Oct 2026 | $1.25 / $4.25 | 1,514 | 1,497–1,532 | #13–112 | ||
| 7 | Gemini 3.8 Flash (High) | Oct 2026 | $0.83 / $4.13 | 1,503 | 1,494–1,512 | #2–30 | |||
| 8 | Claude Opus 5.5 (High) | anthropic | Oct 2026 | $4 / $20 | 1,501 | 1,482–1,519 | #2–11 | ||
| 9 | Kimi K3 (Max) | moonshot | Jun 2026 | $0.24 / $11.94 | 1,500 | 1,491–1,509 | #10–40 | ||
| 10 | claude-opus-4-8-high | anthropic | Sep 2026 | $5 / $25 | 1,496 | 1,490–1,503 | #15–33 | ||
| 11 | Gemini 3.1 Pro Preview | Sep 2026 | $2 / $12 | 1,496 | 1,491–1,501 | #9–36 | |||
| 12 | Gemini 3 Pro | Jan 2026 | — | 1,496 | 1,488–1,503 | #23–91 | |||
| 13 | Muse Spark 1.1 | meta | Sep 2026 | $1.25 / $4.25 | 1,495 | 1,487–1,503 | #21–115 | ||
| 14 | gpt-5.2-chat-latest-20260210 | openai | Feb 2026 | — | 1,495 | 1,487–1,502 | #44–72 | ||
| 15 | Muse Spark | meta | Sep 2026 | — | 1,494 | 1,481–1,507 | #16–41 | ||
| 16 | gpt-5.4-high | openai | Sep 2026 | $2.50 / $15 | 1,493 | 1,486–1,500 | #12–27 | ||
| 17 | Muse Spark 1.3 (Max) | meta | Sep 2026 | $1.25 / $4.25 | 1,491 | 1,479–1,503 | #13–33 | ||
| 18 | qwen3.8-max | alibaba | Oct 2026 | $2 / $6 | 1,490 | 1,481–1,500 | #12–41 | ||
| 19 | Gemini 3.7 Flash (High) | Oct 2026 | $0.75 / $3.75 | 1,490 | 1,480–1,499 | #9–57 | |||
| 20 | gpt-5.6-sol-xhigh | openai | Sep 2026 | $4 / $20 | 1,488 | 1,480–1,496 | #6–24 | ||
| 21 | gemini-3.6-flash-high | Sep 2026 | $0.75 / $3.75 | 1,487 | 1,479–1,496 | #16–95 | |||
| 22 | gpt-5.5-high | openai | Sep 2026 | $5 / $30 | 1,487 | 1,480–1,494 | #9–34 | ||
| 23 | Claude Fable 5.1 (Max) | anthropic | Sep 2026 | $10 / $50 | 1,487 | 1,473–1,501 | #2–22 | ||
| 24 | gpt-6.1-sol-max | openai | Oct 2026 | $2 / $10 | 1,486 | 1,465–1,507 | #1–15 | ||
| 25 | Claude Opus 5 (Max) | anthropic | Sep 2026 | $5 / $25 | 1,486 | 1,477–1,495 | #5–11 | ||
| 26 | claude-opus-4-5-20251101-high-32k | anthropic | Nov 2025 | — | 1,486 | 1,478–1,493 | #36–94 | ||
| 27 | gpt-6-astra-max | openai | Sep 2026 | $10 / $50 | 1,486 | 1,471–1,500 | #1–18 | ||
| 28 | claude-opus-4-5-20251101 | anthropic | Nov 2025 | $5 / $25 | 1,484 | 1,478–1,490 | #19–62 | ||
| 29 | grok-4.20-beta1 | xai | Oct 2026 | — | 1,483 | 1,474–1,493 | #46–119 | ||
| 30 | qwen3.7-max-preview | alibaba | Oct 2026 | — | 1,483 | 1,460–1,505 | #29–73 | ||
| 31 | gpt-5.5-instant | openai | Sep 2026 | — | 1,482 | 1,473–1,492 | #52–114 | ||
| 32 | gemini-3-flash | Jan 2026 | — | 1,482 | 1,473–1,490 | #38–153 | |||
| 33 | mimo-v2.5-pro | xiaomi | Apr 2026 | $0.43 / $0.87 | 1,481 | 1,475–1,488 | #40–129 | ||
| 34 | claude-sonnet-4-6 | anthropic | Sep 2026 | $3 / $15 | 1,481 | 1,475–1,488 | #39–78 | ||
| 35 | gemini-3.5-flash-high | Sep 2026 | $1.50 / $9 | 1,480 | 1,473–1,488 | #10–26 |
Showing Multi-turn exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.