Benchmark
Coding benchmark from Cursor that scores AI models on software-engineering tasks; version 4.0 targets longer tasks. Model makers cite it in release evaluations.
SpaceXAI lists Grok 4.7 at $2 and $6 per million tokens against $10 and $50 for GPT-6 Astra and Claude Fable 5.1, and the only per-task figures in the record put a Cursor run at $4.69 against about $9.
Perspective Coverage
8 publishersReality
Claude Opus 5.5 matched Fable 5.1 on every hidden test in two New Stack coding trials, at $0.75 and $1.42 per run against $1.50 and $1.96. It needed more tokens and more minutes to get there, so the saving holds only for tasks that resemble these.
Reality
Grok 4.7 arrived on Monday after five walked-back timelines, with 40% more parameters and Grok 4.6's list price intact. Cursor's own cost chart still puts its price per task above GPT-6 Astra and Claude Sonnet 5.
Perspective Coverage
3 publishersReality
xAI built Grok 4.7 on a larger base model with a longer reinforcement-learning run and kept the API at Grok 4.6's rates. The open question for buyers is how many tokens the longer runs burn.
Reality
Anthropic held the price on Claude Opus 4.8, cut fast mode to a third of its previous cost, and handed users an effort dial. That combination is what gets agents into engineering budgets.
Reality
Claude Opus 5 is pitched as near-frontier at half the cost. The cost multiple moves with the workload, and every figure on offer is the vendor's own.
Reality
Grok 4.6, Qwen3.8-Max and DeepSeek V4-Pro shipped inside about 24 hours, and two of the three came with downloadable weights. The benchmarks existed to justify a cheaper invoice.
Perspective Coverage
4 publishersReality