The Aggregate: unified LLM rankings, daily
Best AI you can use today: Claude Opus 5.5.
We fold every public benchmark we can find into one daily ranking. Unified rankings for 2137 AI models in the fused corpus across 24310 public benchmarks in the current fit, aggregated from public leaderboards and refreshed daily. Rankings use an Item Response Theory (IRT) fit that maps every model onto one rating scale.
Top models by Aggregate Rating
| Rank | Model | Provider | Rating | Benchmarks |
|---|---|---|---|---|
| 1 | Claude Mythos 5.1 | Anthropic | 2020 ± 29 | 23 |
| 2 | Claude Mythos 5 | Anthropic | 2005 ± 13 | 107 |
| 3 | Claude Opus 5.5 | Anthropic | 1994 ± 6 | 615 |
| 4 | GPT-6 Astra | OpenAI | 1983 ± 4 | 860 |
| 5 | Claude Mythos Preview | Anthropic | 1982 ± 12 | 99 |
| 6 | Gemini 4 Argon | 1978 ± 9 | 311 | |
| 7 | GPT-6 Astra Pro | OpenAI | 1976 ± 23 | 18 |
| 8 | GPT-6.1 Sol | OpenAI | 1968 ± 7 | 459 |
| 9 | Claude Fable 5.1 | Anthropic | 1962 ± 5 | 600 |
| 10 | Claude Sonnet 5.5 | Anthropic | 1941 ± 7 | 403 |
| 11 | Claude Opus 5 | Anthropic | 1934 ± 4 | 1196 |
| 12 | Muse Wonder Full | Meta | 1934 ± 23 | 117 |
| 13 | GPT-6.1 Pro Sol | OpenAI | 1917 ± 28 | 18 |
| 14 | GPT-6 Sol | OpenAI | 1914 ± 7 | 505 |
| 15 | Claude Fable 5 | Anthropic | 1909 ± 4 | 881 |
| 16 | Muse Wonder | Meta | 1906 ± 13 | 162 |
| 17 | GPT-5.5 Pro | OpenAI | 1899 ± 14 | 76 |
| 18 | GPT-5.6 Sol | OpenAI | 1891 ± 3 | 1807 |
| 19 | GPT-5.6 Pro Sol | OpenAI | 1885 ± 14 | 62 |
| 20 | Gemini 3 Deep Think | 1878 ± 23 | 21 |
Which AI is worth paying for?
Premium subscriptions to budget routers. One overall value score. Editorial tier list.
| Plan | Tier | Score / 100 | Price | Verdict |
|---|---|---|---|---|
| Claude Max 20x | S | 86 | USD 200/mo | Higher Claude usage plus a separate monthly API budget for custom apps and agents; credits require claiming and cannot extend interactive plan limits. |
| Claude Max 5x | S | 85 | USD 100/mo | Higher Claude usage plus a separate monthly API budget for custom apps and agents; credits require claiming and cannot extend interactive plan limits. |
| Claude Pro | S | 85 | USD 20/mo | Generous Opus allowance for regular chat and coding in one subscription. |
| ChatGPT Plus | A | 83 | USD 20/mo | A strong all-round bundle; sustained agent work can outgrow its limits. |
| GitHub Copilot Pro+ | A | 82 | USD 39/mo | Premium model choice and a larger published credit pool for regular coding. |
| Google AI Ultra 5x | A | 82 | USD 99.99/mo | Argon in Gemini, Search and Antigravity with higher usage; compare the capacity you will actually use. |
| GitHub Copilot Max | A | 82 | USD 100/mo | A sizeable published coding budget for people who will use the extra credits. |
| Google AI Pro | A | 82 | USD 19.99/mo | Argon in Gemini and Search, plus premium Claude in Antigravity; Argon coding access requires Ultra. |
Latest leaderboard changes
- Claude Opus 5.5 (Max) took the lead on SWE-bench Pro (Opus 5 & Mythos 5.1 System Cards) (89.9 vs 81.2 by Claude Fable 5.1 (Max))
- Gemini 4 Argon took the lead on Icelandic LLM - Famous Phrases (36.19 vs 30.88 by Gemini 3.8 Flash)
- Gemini 4 Argon took the lead on EKI Estonian LLM - Trivia (90 vs 85 by Gemini 3.1 Pro (Preview))
- Muse Wonder Full took the lead on Vals AI Vibe Code Bench 1-100 (33.98 vs 30.36 by Claude Opus 5.5)
- Gemini 4 Argon took the lead on Next.js Agent Evals (OpenCode) - Success Rate (97 vs 94 by Grok 4.7)
- Gemini 4 Argon (High) took the lead on Humanity's Sixth Sense (55.4 vs 53.6 by GPT-6 Astra (Max))
- Gemini 4 Argon took the lead on EKI Estonian LLM - Language Advice (77.5 vs 76.04 by GPT-6 Astra)
- Gemini 4 Argon took the lead on Icelandic LLM - Idiom Completion (75.96 vs 75.03 by Claude Opus 5.5)
Explore: all models · benchmark catalog · capability trends · daily changes
Interactive version: theaggregate.ai/ · How It Works · Data refreshed daily, snapshot 2026-10-15.