claude-fable-5
100.0%±0.0%
100.0%CI100.0%
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 14 min14 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· 14 minutes ago
- SWE-bench· 14 minutes ago
- Terminal-Bench· 14 minutes ago
- ARC-AGI-2· 14 minutes ago
Filter by org:
Released:
claude-fable-5-1
100.0%±0.0%
100.0%CI100.0%
claude-opus-5-5
100.0%±0.0%
100.0%CI100.0%
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 | Anthropic | Sep 2026 | $10 / $50 | 100.0% | 100.0%–100.0% | #4–21 | ||
| 2 | claude-fable-5-1 | Anthropic | Sep 2026 | $10 / $50 | 100.0% | 100.0%–100.0% | #2–22 | ||
| 3 | claude-opus-5-5 | Anthropic | Oct 2026 | $4 / $20 | 100.0% | 100.0%–100.0% | #2–11 | ||
| 4 | claude-sonnet-5-5 | Anthropic | Oct 2026 | $2 / $10 | 100.0% | 100.0%–100.0% | #4–26 | ||
| 5 | gemini-4-argon | Google DeepMind | Oct 2026 | $2 / $10 | 100.0% | 100.0%–100.0% | #1–10 | ||
| 6 | gpt-5.5-pre-release | OpenAI | — | — | 100.0% | 100.0%–100.0% | #22–36 | ||
| 7 | gpt-5.5-pro-pre-release | OpenAI | — | — | 100.0% | 100.0%–100.0% | #22–60 | ||
| 8 | gpt-5.6-sol | OpenAI | Sep 2026 | $4 / $20 | 100.0% | 100.0%–100.0% | #6–24 | ||
| 9 | gpt-6-astra | OpenAI | Sep 2026 | $10 / $50 | 100.0% | 100.0%–100.0% | #1–18 | ||
| 10 | gpt-6-sol | OpenAI | Oct 2026 | $2 / $10 | 100.0% | 100.0%–100.0% | #7–53 | ||
| 11 | gpt-6.1-sol | OpenAI | Oct 2026 | $2 / $10 | 100.0% | 100.0%–100.0% | #1–15 | ||
| 12 | qwen3.8-max-0902 | Alibaba | Oct 2026 | $2 / $6 | 100.0% | 100.0%–100.0% | #23–155 | ||
| 13 | gpt-5.6-terra | OpenAI | Sep 2026 | $2 / $12 | 99.7% | 99.4%–100.0% | #13–60 | ||
| 14 | muse-wonder-1.0 | Meta AI | — | — | 99.4% | 99.1%–99.8% | #69–128 | ||
| 15 | qwen3.8-max | Alibaba | Oct 2026 | $2 / $6 | 99.4% | 99.1%–99.8% | #12–41 | ||
| 16 | grok-4.6 | xAI | Sep 2026 | $2 / $6 | 99.2% | 98.7%–99.6% | #15–52 | ||
| 17 | muse-spark-1.3 | Meta AI | Sep 2026 | $1.25 / $4.25 | 99.2% | 98.6%–99.8% | #13–33 | ||
| 18 | claude-haiku-5-5 | Anthropic | Oct 2026 | $0.10 / $0.50 | 98.9% | 98.4%–99.4% | #43–277 | ||
| 19 | claude-opus-5 | Anthropic | Sep 2026 | $5 / $25 | 98.9% | 97.8%–100.0% | #5–11 | ||
| 20 | gemini-3.8-flash | Google DeepMind | Oct 2026 | $0.83 / $4.13 | 98.9% | 98.0%–99.8% | #2–30 | ||
| 21 | gpt-6-luna | OpenAI | Oct 2026 | $0.10 / $0.50 | 98.9% | 98.2%–99.6% | #31–85 | ||
| 22 | deepseek-v4-pro-0813 | DeepSeek | Aug 2026 | $0.66 / $1.98 | 98.6% | 97.6%–99.6% | #40–130 | ||
| 23 | claude-opus-4-8 | Anthropic | Sep 2026 | $5 / $25 | 98.3% | 96.9%–99.7% | #15–33 | ||
| 24 | deepseek-v4.1-flash | DeepSeek | Oct 2026 | $0.30 / $1.20 | 98.3% | 97.7%–99.0% | #14–30 | ||
| 25 | gpt-5.6-luna | OpenAI | Sep 2026 | $0.20 / $1.20 | 98.3% | 97.2%–99.5% | #30–147 | ||
| 26 | mistral-large-4-0 | Mistral AI | — | $0.68 / $2.09 | 98.3% | 97.7%–99.0% | #55–288 | ||
| 27 | grok-4.7 | xAI | Oct 2026 | $2 / $6 | 98.1% | 96.6%–99.5% | #23–72 | ||
| 28 | Muse-Spark-Open-816B-A42B | Meta AI | — | — | 98.1% | 96.8%–99.3% | #54–119 | ||
| 29 | claude-opus-4-7 | Anthropic | Sep 2026 | $5 / $25 | 97.8% | 95.6%–100.0% | #1–18 | ||
| 30 | gpt-5.4-2026-03-05 | OpenAI | Sep 2026 | $2.50 / $15 | 97.8% | 95.6%–100.0% | #12–27 | ||
| 31 | grok-4.5 | xAI | Sep 2026 | $2 / $6 | 97.8% | 96.5%–99.1% | #29–70 | ||
| 32 | gemini-3.7-flash | Google DeepMind | Oct 2026 | $0.75 / $3.75 | 97.2% | 95.4%–99.1% | #9–57 | ||
| 33 | kimi-k3 | Moonshot | Jun 2026 | $0.24 / $11.94 | 97.2% | 96.1%–98.3% | #10–40 | ||
| 34 | deepseek-v4-pro | DeepSeek | Aug 2026 | $0.66 / $1.98 | 96.7% | 94.7%–98.7% | #17–55 | ||
| 35 | gpt-5.2-2025-12-11 | OpenAI | Dec 2025 | $1.75 / $14 | 96.1% | 93.5%–98.7% | #34–93 |
Showing AIME (math) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.