Gemini 4 Argon Hits 97.5% on ARC-AGI-3, Second Model Family to Max It Out
rbhar90 · x · 2026-10-16
ARC Prize published Google's Gemini 4 Argon results on ARC-AGI (Verified):
- ARC-AGI-3: 97.5% ($4.8K via provider adapter harness), 49.8% ($5.8K) on the standard harness
- ARC-AGI-2: 91.3% at $0.32/task
- ARC-AGI-1: 98.5% at $0.16/task
ARC Prize's Mike Knoop notes Argon is only the second model family to officially, effectively max out ARC-AGI-3 via a provider adapter, crediting Google DeepMind. He also highlights a notable shared pattern: the same "backwards bend" in action efficiency seen across frontier models.
Related event: Gemini 4 Argon Tops ARC-AGI-3 at 97.5%, Second Lab to Break 95%(5 posts)→
More from Models
- ChatGPT's 'best AI video tool' answer points to Runway integration, sparking ad doubts — tlakomy · 2026-10-16
- Microsoft's MAI finishes in-house 3T-parameter pretrained base models, post-training results coming — soumitrashukla9 · 2026-10-16
- Hands-on with Gemini 4 Argon: faster than Opus 5.5 but hallucinates more and costs more — prasenx · 2026-10-16
- Bindu Reddy urges Meta to open-source Wonder, claiming it beats DeepSeek — bindureddy · 2026-10-16
- Fortytwo Engine boosts Qwen3.8-27B accuracy 7% and cuts tokens 25% via Swarm Inference — rohanpaul_ai · 2026-10-16
- "China Has Caught Up to the Frontier"? Benchmark Chart Says It Hasn't Even Passed Microsoft — scaling01 · 2026-10-16