GPT-6.1 Terra benchmarks: near-Astra scores at a fraction of the cost
testingcatalog · x · 2026-10-27
Benchmark charts (shared by testingcatalog, sourcing OpenAI's cost-vs-score curves) for GPT-6.1 Terra:
- Agents' Last Exam v1: Terra hits 59% at roughly $0.3 of compute, close to what GPT-6 Astra only reaches at $7+, while Claude Opus 5.5 tops the chart at 63% for $8.5
- MMMU-Pro (Vision): Terra reaches 85.5% at about $0.005, essentially matching Astra at dozens of times the cost
Consistent with the launch messaging: Terra trades a bit of peak score for an order-of-magnitude cost drop, competing on price-per-task.
More from Models
- Poster surprised that v4.1 flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Dev claims Anthropic is baking 'sabotage' into model behavior for 'wrong' engineering — cephaloform · 2026-10-27
- Gemini fails at listing unread emails, tells user to search Gmail manually — gethackteam · 2026-10-27
- Meta's Muse Spark Open goes live on Applied Compute for async RL post-training — ypatil125 · 2026-10-27
- Moonshot curbs hacking ability in Kimi K3.1 Pro, its strongest 3T-class open-weight model — pstAsiatech · 2026-10-27
- Would you want an argumentative LLM that never backs down, even under prompt injection? — GodComplecs · 2026-10-27