Artificial Analysis Intelligence Index v4.0
Version 4.0 of Artificial Analysis's index, ten evaluations in four equal categories that brought in real-world knowledge work and hallucination tests.
Launched about 6 January 2026 and in use until June 2026. Added GDPval-AA, AA-Omniscience and CritPt, and dropped MMLU-Pro, LiveCodeBench and AIME 2025. Components: GDPval-AA, τ²-Bench Telecom, Terminal-Bench Hard (44 tasks), SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond and CritPt. Agents, Coding, General and Scientific Reasoning each weigh 25%. Top models scored 50 or less, against 73 on v3.
- Made by
- Artificial Analysis
- Released
- January 2026
- Kind
- Composite indices
- Scored
- Checked automatically
- Answers
- Agent task
- Strongest model tested
- GPT-5.5 #20 on the capability index
- Last in a launch post
- May 2026, dropped for a newer version
- Last model added
- May 2026
GPT-5.5 leads with 60.2 among models released by May 2026
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in May 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 15 more
- 1 GPT-5.5 60.2
- 2 GLM-5 50.0
- 3
MiniMax-M2.7 50.0 - 4 MiniMax-M2.5 42.0
- 5
Command A+ 37.0
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 60.2 | Apr 2026 | Lab model card | |
| 2 | GLM-5 | 50.0 | Feb 2026 | Lab model card | |
| 3 | MiniMax-M2.7 | 50.0 | Mar 2026 | Lab model card | |
| 4 | MiniMax-M2.5 | 42.0 | May 2026 | Lab model card | |
| 5 | Command A+ | 37.0 | May 2026 | Lab model card |
2 models have held number one in labs’ own numbers since its release in January 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs headline it less often now, last in May 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| May 20, 2026 | Command A+ | 37 | Artificial Analysis Intelligence Index (quoted by Cohere) |
| Apr 23, 2026 | GPT-5.5 | 60.2 | Artificial Analysis Intelligence Index (GPT-5.5 xhigh) |
| Mar 18, 2026 | MiniMax-M2.7 | 50 | Artificial Analysis |
3 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| May 26, 2026 | MiniMax-M2.7 technical report | 50 | Artificial Analysis (Intelligence Index), printed bar label (Figure 1) | Capabilities |
| May 26, 2026 | MiniMax-M2.5 technical report | 42 | Artificial Analysis (Intelligence Index), printed bar label (Figure 1) | Capabilities |
| Feb 17, 2026 | GLM-5 technical report | 50 | Artificial Analysis Intelligence Index v4.0 (text, Figure 2) | Capabilities |
Versions
More in Other
- Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
- SAGE v1.1 (Vals) In use Models grade handwritten undergraduate math and computer science work against rubrics. Scored by class-balanced accuracy of each rubric check against expert grading. Claude Opus 5.5 91.3%
- MTEB Fading Massive Text Embedding Benchmark: retrieval, clustering, classification across languages and modalities.
sonar 42% - Anthropic ECI (AECI) Only in system cards Index that combines a basket of capability benchmarks into one capability score to track trends across Anthropic models. Claude Opus 5.5 169.4
- SPEED-Bench Only in system cards Measures speculative decoding across varied prompts and domains. Reports the average acceptance length of draft tokens, so higher means faster generation at the same output.
Nemotron 3 Ultra 5.15 - Qwen in-house English automatic evaluation Only in system cards Models answer Qwen in-house English datasets on knowledge, comprehension, coding, math and related skills. Skills and weights change between reports.
Qwen2-72B 72.9%