GPT-6.1 Terra

OpenAIUnpriced

Score basis

GPT-6.1 Terra has too few ranked results yet to rate it on any capability.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability.

No capability has enough ranked results to rate yet.

No current price is tracked for this model. See the rate card

19results on19benchmarks

From 3 sources · latest Oct 26, 2026 · How verification works

19 results on 19 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Benchmarks outside the capability baskets. They are not ranked against a leader.

MentalHealthBench (emergent)
52.90—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
MentalHealthBench (overall)
55.50—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Dynamic Self-harm
0.88—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Dynamic Emotional reliance
0.97—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Dynamic Mental health
0.99—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
HealthBench Consensus length-adjusted
95.10—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026

Show 13 more resultsHide 13 results

Biology Model Refusal Evaluation - Benign (Not over-refuse)
0.98—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Biology Model Refusal Evaluation - Dual Use (Safe)
0.96—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Biology Model Refusal Evaluation - Severe (Safe)
0.99—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Coronavirus–ACE2 Cell-Entry Screen
0.47—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Cybersecurity Safety Evaluation - Production Chat
0.98—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Cybersecurity Safety Evaluation - Semi-Synthetic Agentic Envs
0.97—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Cybersecurity Safety Evaluation - Synthetic Agentic Envs
1.00—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
HealthBench Hard length-adjusted
31.40—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
HealthBench length-adjusted
55.10—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
HealthBench Professional length-adjusted
62.70—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
Internal Research Debugging Evaluation (mean rubric score)
76.39—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
KernelGen 1P
45.34—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026
SHP2 Protein Function Prediction
0.37—
Vendordeploymentsafety.openai.comgpt-6-1-terra
Oct 26, 2026

GPT-6.1 Terra is made by OpenAI.

We track 19 results for GPT-6.1 Terra on 19 benchmarks from 3 sources. The latest was recorded on Oct 26, 2026.

Where GPT-6.1 Terra's numbers come from, and every name it appears under.

Verification: 19 scores · 0 independently verified · 19 vendor-reported. How these tiers are assigned

From 3 sources on 1 site. deploymentsafety.openai.com supplies all of them. Bars are coloured by trust tier.