Leaked GPT-6.1 Terra benchmarks: cheap but 'boring', still far behind Astra and Claude
Angaisb_ · x · 2026-10-27
Leaked benchmark charts show GPT-6.1 Terra scoring 56-60% on Agents' Last Exam v1 (vs 63% for Claude Opus 5.5 and higher-cost GPT-6 Astra), 83-86% on MMMMU-Pro Vision at half the cost of GPT-6.1 Sol, and 60-75% on OSWorld 2.1 offline — below Claude Sonnet 5.5 and Astra.
The poster calls the results "boring": Terra looks like an incremental low-cost tier, with the real upgrade expected in the unreleased GPT-6.1/6.5 Astra.
Related event: GPT-6.1 Terra benchmarks leak with half the cost(4 posts)→
More from Models
- KOL defends B-tier rating for GPT-6.1 Sol, blames OpenAI's botched release naming — Angaisb_ · 2026-10-27
- php2shell exploit benchmark: only 2 of 5 frontier models can port the bug — xeophon · 2026-10-27
- Qwen Code v0.26.2-preview.0 adds session permission rules and experimental shared agent loop — qwen-code-review-bot · 2026-10-27
- GPT-6.1 Terra cuts factual error rate from 22.3% to 4.3%, an ~81% drop — haider1 · 2026-10-27
- GPT-6.1 Terra lands: early users praise speed, value and subagent performance — BenBajarin · 2026-10-27
- Artificial Analysis Ships Intelligence Index v4.3.2 With GPT-6.1 Terra Comparison — ArtificialAnlys · 2026-10-27