GPT-6.1 Terra hits 78.5 on Browser Use Benchmark, near Sol at 35% less cost
sandersted · x · 2026-10-27
browseruse reports GPT-6.1 Terra scored 78.5 on the Browser Use Benchmark (v2.1: 160 shared scored tasks, 16 models), nearly matching GPT-6.1 Sol's 79.7 at 35% lower cost, keeping the Pareto frontier with OpenAI. The chart also shows Kimi K3.1 Pro at 76.8, Opus 5.5 at 74.9, Grok 4.7 at 73.4, and DeepSeek V4.1 Flash at 70.6, with Terra high dominating the price-performance frontier under $1 per task.
More from coding & agent
- Querio launches: analytics platform that puts your data stack in a git repo for AI agents — thetripathi58 · 2026-10-28
- Stop conflating "harness": labs build the pilot, companies build the mech — robleclerc · 2026-10-28
- MiRL: error-targeted RL cuts terminal agent misbehaviors 43-57% — _akhaliq · 2026-10-28
- Vjeux's AI agents hit 2.6x speedups on Open Kernel Challenge kernels, then stalled — Vjeux · 2026-10-28
- Judgment Labs opens access as a monitoring layer for long-horizon AI agents — alifcoder · 2026-10-28
- Anthropic Reveals 12 New Prompting Rules for Claude Opus 5.5 — JeremyCMorgan · 2026-10-28