AA Intelligence Index v5.0: Gemini 4 Carbon tops at 59 with no public API
cgarciae88 · x · 2026-10-29
A post marveling at how fast the leaderboard moves ("this changes so quickly") shares the Artificial Analysis Intelligence Index v5.0, which combines 9 evals: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1.
Rankings: Gemini 4 Carbon (high) leads at 59 but is flagged "no publicly available API"; Claude Opus 5.5 (max, fallback) 58, GPT-6 Astra (max) 57, GPT-6.1 Sol 55, Claude Sonnet 5.5 54, GPT-6.1 Terra 51, Gemini 4 Argon 50, Muse Wonder Full 50, Claude Fable 5.1 49.
More from Models
- Artificial Analysis v5 reranking: theo mocks open-weight vs Opus 5.5 claims — ivan_bezdomny · 2026-10-29
- Rumor: OpenAI pushes big release to tomorrow, possibly due to Gemini 4 Carbon — mark_k · 2026-10-29
- Gemini 4.0 Carbon's security praised, but mocked for losing the "felony bench" — vitaliychiley · 2026-10-29
- Google hits frontier on private benchmarks yet stock plunges 8% after hours — bookwormengr · 2026-10-29
- Dev praises gpt-6-luna's price-performance, calls opus-5.5 best for implementation — emax · 2026-10-29
- Meta researcher marvels at Gemini's progress in under 6 months, sharing a suspicious leaderboard — armandjoulin · 2026-10-29