GPT-6.1 Terra hits GBENCH: $0.03 for 85.6th percentile, OpenAI now owns the Pareto frontier
sandersted · x · 2026-10-28
GBENCH, a benchmark probing real intelligence via complex games, published GPT-6.1 Terra coding results: OpenAI models now dominate the Pareto front, with GPT-6 Astra at 82.9 GScore and GPT-6.1 Sol at 81.6 ranking 1-2, while Terra (75.1, 4th) lands between Claude Opus 5.5 (76.5) and Gemini 4 Argon (72.4) — yet on the cost-efficiency chart Terra hits the 85.6th percentile at just $0.03, an outlier on the frontier. The author still uses Opus 5.5 for about half of coding-assistant work for its more usable behavior.
More from Models
- Tencent's Hy-SimulMT-30B-A3B-FP8 translation model trends on Hugging Face — tencent · 2026-10-28
- Google reportedly launches Genie 4, its strongest world model yet — oran_ge · 2026-10-28
- Grok Bot reportedly building Discord support, Slack and Teams bots coming — nima_owji · 2026-10-28
- Kimi K3.1 scores 38% on RareBench, matching GPT-6 Astra at a quarter of the cost — danielmckinn0n · 2026-10-28
- 48 local models tested as agents on M1 Max 64GB: qwen3.8-27b tops real-world score — HAVT_ · 2026-10-28
- GPT-6 Astra hits SOTA on ARC-AGI-3, inventing its own programming language — typewriters · 2026-10-28