@AnthropicAI: Correction: Claude Opus 4's ~3x average speedup dates to May 2025, not May 2024. This evaluation has only existed since…
Summary
Anthropic issued a correction clarifying that Claude Opus 4's ~3x average speedup dates to May 2025, not May 2024, and that earlier models from May 2024 showed no speedup on the backtested evaluation.
Similar Articles
@AnthropicAI: Each time we release a model, we run the same test: give it code that trains a small AI model, ask the new model to spe…
Anthropic shares internal benchmark results showing dramatic AI coding improvement: while Claude Opus 4 averaged ~3x speedup on an ML code optimization task in May 2024, the new Mythos Preview model achieved ~52x speedup this April, compared to 4-8 hours for a skilled human to reach 4x.
@rohanpaul_ai: Fast mode for Claude Opus 4.8 is roughly 2.5x the speed while being 3X cheaper than before. AI/ML API (@aimlapi) alread…
Claude Opus 4.8 now has a fast mode that is 2.5x faster and 3x cheaper, integrated on AI/ML API with free access for selected users.
@rohanpaul_ai: Anthropic says Opus 5.5 may notice when it’s under evaluation, making clean eval behavior harder to generalize to actua…
Anthropic reports that their Claude Opus 5.5 model may detect evaluation scenarios, complicating the generalization of observed behavior to real deployments. The model offers performance comparable to Fable 5.1 with a 40% cost reduction and faster output.
Vals AI moves its prediction for full recursive AI self-improvement to July 2027. Claude Opus 5.5 tops its autonomous AI research benchmark, becoming the first model to outperform a published human reference in AI model training.
Vals AI updated its forecast for full recursive AI self-improvement to July 2027, as Claude Opus 5.5 became the first model to beat a published human reference on an autonomous AI research benchmark.
Claude Opus 4.8 says it's the only model that finished every case on the Super-Agent benchmark. Anyone run it on real agents yet?
Anthropic released Claude Opus 4.8, claiming it is the only model to complete every case on the Super-Agent benchmark and that it outperforms GPT-5.5 on browser/computer use tasks with better tool efficiency and fewer uncorrected code flaws.