Benchmark leaderboard - 25 entries
Artificial Analysis Intelligence Index leaderboard
Artificial Analysis Intelligence Index combines a comprehensive suite of evaluation datasets to assess language model capabilities across reasoning, knowledge, maths and programming. As of October 17, 2026, Claude Opus 5.5 (max with fallback) ranks first on the Artificial Analysis Intelligence Index board with 58.
Last verified from artificialanalysis.ai. Read the caveats
Artificial Analysis Intelligence Index
25 entries, in the board's order
| 1 | Claude Opus 5.5 (max with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 1 of 134; reasoning effort: max with fallback Official leaderboard | 58 |
| 2 | Claude Sonnet 5.5 (max with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 2 of 134; reasoning effort: max with fallback Official leaderboard | 56 |
| 3 | Claude Opus 5.5 (xhigh with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 3 of 134; reasoning effort: xhigh with fallback Official leaderboard | 56 |
| 4 | Muse Wonder Full (max) Intelligence Index v4.3.2 (10 evaluations); creator: Meta; rank 4 of 134; reasoning effort: max Official leaderboard | 56 |
| 5 | Claude Opus 5.5 (high with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 5 of 134; reasoning effort: high with fallback Official leaderboard | 54 |
| 6 | Claude Fable 5.1 (max with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 6 of 134; reasoning effort: max with fallback Official leaderboard | 53 |
| 7 | Claude Fable 5.1 (xhigh with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 7 of 134; reasoning effort: xhigh with fallback Official leaderboard | 53 |
| 8 | GPT-6 Astra (max) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 8 of 134; reasoning effort: max Official leaderboard | 53 |
| 9 | Gemini 4 Argon (high) Intelligence Index v4.3.2 (10 evaluations); creator: Google; rank 9 of 134; reasoning effort: high Official leaderboard | 53 |
| 10 | Muse Wonder (max) Intelligence Index v4.3.2 (10 evaluations); creator: Meta; rank 10 of 134; reasoning effort: max Official leaderboard | 52 |
| 11 | GPT-6 Astra (xhigh) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 11 of 134; reasoning effort: xhigh Official leaderboard | 52 |
| 12 | Claude Sonnet 5.5 (xhigh with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 12 of 134; reasoning effort: xhigh with fallback Official leaderboard | 52 |
| 13 | GPT-6.1 Sol (max) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 13 of 134; reasoning effort: max Official leaderboard | 52 |
| 14 | Claude Opus 5.5 (medium with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 14 of 134; reasoning effort: medium with fallback Official leaderboard | 51 |
| 15 | Claude Fable 5.1 (high with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 15 of 134; reasoning effort: high with fallback Official leaderboard | 51 |
| 16 | GPT-6.1 Sol (xhigh) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 16 of 134; reasoning effort: xhigh Official leaderboard | 51 |
| 17 | GPT-6 Astra (high) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 17 of 134; reasoning effort: high Official leaderboard | 51 |
| 18 | GPT-6.1 Sol (high) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 18 of 134; reasoning effort: high Official leaderboard | 50 |
| 19 | GPT-6 Astra (medium) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 19 of 134; reasoning effort: medium Official leaderboard | 50 |
| 20 | Claude Fable 5.1 (medium with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 20 of 134; reasoning effort: medium with fallback Official leaderboard | 49 |
| 21 | Muse Spark 1.3 (max) Intelligence Index v4.3.2 (10 evaluations); creator: Meta; rank 21 of 134; reasoning effort: max Official leaderboard | 48 |
| 22 | GPT-6.1 Sol (medium) Intelligence Index v4.3.2 (10 evaluations); creator: OpenAI; rank 22 of 134; reasoning effort: medium Official leaderboard | 48 |
| 23 | Claude Fable 5.1 (low with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 23 of 134; reasoning effort: low with fallback Official leaderboard | 47 |
| 24 | Claude Sonnet 5.5 (high with fallback) Intelligence Index v4.3.2 (10 evaluations); creator: Anthropic; rank 24 of 134; reasoning effort: high with fallback Official leaderboard | 47 |
| 25 | Grok 4.7 (xhigh) Intelligence Index v4.3.2 (10 evaluations); creator: SpaceXAI; rank 25 of 134; reasoning effort: xhigh Official leaderboard | 46 |
About this board
- Rank 25 is a tie at score 46: Grok 4.7 (high), MiMo-V2.6-Pro (top open-weights model per the leaderboard FAQ) and GPT-6 Astra (low) also score 46 but fall at listed positions 26-28, so they are excluded from the top 25.
- The leaderboard shows no per-model evaluation date; the date column is the read date 2026-10-17. Index version (v4.3.2, 10 evaluations) and the description come from https://artificialanalysis.ai/methodology/intelligence-benchmarking.
FAQ
What does Artificial Analysis Intelligence Index measure?
Artificial Analysis Intelligence Index combines a comprehensive suite of evaluation datasets to assess language model capabilities across reasoning, knowledge, maths and programming.
Which model leads Artificial Analysis Intelligence Index?
As of October 17, 2026, Claude Opus 5.5 (max with fallback) ranks first on the Artificial Analysis Intelligence Index board with 58. That is the board's own order, not a Developers Digest ranking.
Where do these Artificial Analysis Intelligence Index scores come from?
All 25 entries come from the official leaderboard at artificialanalysis.ai. Every entry links to its source, which was read on October 17, 2026, and lists the setting it was run under.
Related reading
- Muse Spark Open Weights: 816B Model, Benchmarks, and How to Run ItMeta released Muse Spark Open weights on October 15, 2026: 816B total, 42B active, 1M context. Run recipes, hardware floor, license catch, and where it trails.
- Step 5 Preview: Pricing, Benchmarks and the October 15 Open WeightsStep 5 Preview is StepFun's 600B MoE with 27B active and a 1M window. What it scores, what a session costs, and what to check before the October 15 weights.
- GPT-6 Astra Release Guide: Benchmarks, $10/$50 Pricing, and How to Run It in Codex and OpenCodeGPT-6 Astra release guide: OpenAI's max-capability model, its $10/$50 pricing and 1.05M context, what the benchmarks do and do not say, and commands to try it.
- Cloudflare Page Shield ML Caught 4 Storefront Malware Campaigns Static Scanners MissedCloudflare Page Shield ML caught four malicious JavaScript campaigns on storefronts that static scanners missed. How each hid, and why behavior beat signatures.
- Weekly Highlights: Cheaper Agents, Harder QuestionsClaude Code made auto mode the default, Gemini 3.7 Flash halved workhorse pricing, DeepSeek open-sourced its harness, and SQLite fixed a 16-year-old data race.
- Grok 4.6: xAI's Agent-Focused Update Matches GPT-5.6 Sol at the Same $2/$6 PriceGrok 4.6 release guide: xAI's agent-focused update matches GPT-5.6 Sol on the AA index at the same $2/$6 pricing, and runs in Cursor and OpenCode.
Sources
Last verified . Each row links to the page its score was copied from.
Newsletter
Get new benchmark results as they land
One email per week. New model releases, the leaderboard moves that matter and what they mean for what you build.