Back

OpenAI

GPT-6.1 Terra

ReasoningClosed weights
Intelligence
41.3
Rank 64 of 759 measured models
Output speed
90.9 t/s
Rank 227 of 418 measured models
Price/1M
$2
Rank 485 of 694 measured models
Context window
1M
Rank 92 of 1272 measured models
Cost per task
$0.0953
Rank 52 of 211 measured models

GPT-6.1 Terra (Medium) scores 41.3 on the Artificial Analysis Intelligence Index, ranking 64th of 759 measured models. The closest models on this index are Claude Opus 4.8 (batch) (41.8), Ling 3.1 Flash (41.1), and Gemini 3.8 Flash (40.9). At $2 per million tokens (3:1 input/output blended price), it is cheaper than Claude Opus 4.8 (batch) ($5), more expensive than Ling 3.1 Flash ($0.45) and Gemini 3.8 Flash ($1.50). With an output speed of 90.9 t/s, it is slower than Ling 3.1 Flash (214 t/s) and Gemini 3.8 Flash (134 t/s).

Artificial Analysis Indices
Medium
Intelligence41.3
Rank 64 of 759 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Cost per task
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting42.7
Rank 69 of 233 measured models
Strategy & Ops45.4
Rank 70 of 233 measured models
Legal45.5
Rank 64 of 233 measured models
Engineering41.7
Rank 67 of 232 measured models
Economics48.6
Rank 73 of 240 measured models
Standard Benchmarks
HLE40.2%
Rank 91 of 678 measured models
SciCode51.6%
Rank 98 of 245 measured models
AA-LCR80.7%
Rank 71 of 589 measured models
Terminal-Bench v432.3%
Rank 48 of 232 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy