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 knowledge work, coding, science, and general knowledge. As of November 7, 2026, Gemini 4 Carbon (high) ranks first on the Artificial Analysis Intelligence Index board with 60.
Last verified from artificialanalysis.ai. Read the caveats
Artificial Analysis Intelligence Index
25 entries, in the board's order
| 1 | Gemini 4 Carbon (high) Intelligence Index v5.0.1 (9 evaluations); creator: Google; rank 1 of 99; reasoning effort: high Official leaderboard | 60 |
| 2 | Claude Opus 5.5 (max) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 2 of 99; reasoning effort: max (FAQ label: Max, Default Fallback) Official leaderboard | 59 |
| 3 | Gemini 4 Carbon (medium) Intelligence Index v5.0.1 (9 evaluations); creator: Google; rank 3 of 99; reasoning effort: medium Official leaderboard | 58 |
| 4 | Claude Opus 5.5 (xhigh) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 4 of 99; reasoning effort: xhigh (FAQ label: Xhigh, Default Fallback) Official leaderboard | 57 |
| 5 | GPT-6 Astra (max) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 5 of 99; reasoning effort: max Official leaderboard | 57 |
| 6 | GPT-6 Astra (xhigh) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 6 of 99; reasoning effort: xhigh Official leaderboard | 55 |
| 7 | GPT-6 Astra (high) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 7 of 99; reasoning effort: high Official leaderboard | 55 |
| 8 | GPT-6.1 Sol (max) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 8 of 99; reasoning effort: max Official leaderboard | 55 |
| 9 | Claude Sonnet 5.5 (max) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 9 of 99; reasoning effort: max Official leaderboard | 55 |
| 10 | Gemini 4 Carbon (low) Intelligence Index v5.0.1 (9 evaluations); creator: Google; rank 10 of 99; reasoning effort: low Official leaderboard | 54 |
| 11 | GPT-6.1 Sol (xhigh) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 11 of 99; reasoning effort: xhigh Official leaderboard | 52 |
| 12 | Claude Opus 5.5 (high) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 12 of 99; reasoning effort: high Official leaderboard | 52 |
| 13 | GPT-6 Astra (medium) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 13 of 99; reasoning effort: medium Official leaderboard | 52 |
| 14 | GPT-6.1 Terra (max) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 14 of 99; reasoning effort: max Official leaderboard | 51 |
| 15 | Gemini 4 Argon (high) Intelligence Index v5.0.1 (9 evaluations); creator: Google; rank 15 of 99; reasoning effort: high Official leaderboard | 50 |
| 16 | GPT-6.1 Sol (high) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 16 of 99; reasoning effort: high Official leaderboard | 50 |
| 17 | Muse Wonder Full (max) Intelligence Index v5.0.1 (9 evaluations); creator: Meta; rank 17 of 99; reasoning effort: max Official leaderboard | 50 |
| 18 | Claude Fable 5.1 (xhigh) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 18 of 99; reasoning effort: xhigh Official leaderboard | 50 |
| 19 | Claude Sonnet 5.5 (xhigh) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 19 of 99; reasoning effort: xhigh Official leaderboard | 50 |
| 20 | Claude Fable 5.1 (max) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 20 of 99; reasoning effort: max Official leaderboard | 49 |
| 21 | Claude Opus 5.5 (medium) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 21 of 99; reasoning effort: medium Official leaderboard | 48 |
| 22 | Claude Fable 5.1 (high) Intelligence Index v5.0.1 (9 evaluations); creator: Anthropic; rank 22 of 99; reasoning effort: high Official leaderboard | 47 |
| 23 | Kimi K3.1 Pro Intelligence Index v5.0.1 (9 evaluations); creator: Kimi; rank 23 of 99; highest-ranked open weights model per the leaderboard FAQ Official leaderboard | 46 |
| 24 | GPT-6.1 Sol (medium) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 24 of 99; reasoning effort: medium Official leaderboard | 46 |
| 25 | GPT-6.1 Terra (xhigh) Intelligence Index v5.0.1 (9 evaluations); creator: OpenAI; rank 25 of 99; reasoning effort: xhigh Official leaderboard | 45 |
About this board
- Rank 25 is GPT-6.1 Terra (xhigh) at 45; the next listed model, Muse Wonder (max), scores 44, so there is no tie at the cutoff. The leaderboard FAQ counts 99 ranked models.
- The leaderboard shows no per-model evaluation date; the date column is the read date 2026-11-07. Index version (v5.0.1, 9 evaluations, November 2026 to current) 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 knowledge work, coding, science, and general knowledge.
Which model leads Artificial Analysis Intelligence Index?
As of November 7, 2026, Gemini 4 Carbon (high) ranks first on the Artificial Analysis Intelligence Index board with 60. 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 November 7, 2026, and lists the setting it was run under.
Related reading
- Gemini 4 Carbon: Benchmarks, Pricing, and AccessGemini 4 Carbon is Google's new frontier model: 59 on the AA Intelligence Index, $2/$10 intro pricing, but cyber-defender access only. What builders do now.
- Mistral Large 4 on Hugging Face: Weights, License, vLLM SetupMistral Large 4 weights are on Hugging Face under a modified MIT license. What the license blocks, the vLLM command, and when self-hosting beats the API.
- 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.
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.