OpenAI

GPT-6.1 Terra

Intelligence
38.2
Rank 71 of 790 measured models
Output speed
62.2 t/s
Rank 329 of 456 measured models
Price/1M
$2
Rank 519 of 741 measured models
Context window
1M
Rank 107 of 1368 measured models
Cost per task
$0.169
Rank 67 of 235 measured models

GPT-6.1 Terra (Medium) scores 38.2 on the Artificial Analysis Intelligence Index, ranking 71st of 790 measured models. The closest models on this index are Grok 4.5 (High) (38.8), GPT-5.5 (38.4), and Claude Sonnet 5 (38.2). At $2 per million tokens (3:1 input/output blended price), it is cheaper than Grok 4.5 (High) ($3), GPT-5.5 ($11.25), and Claude Sonnet 5 ($4). With an output speed of 62.2 t/s, it is about as fast as Grok 4.5 (High) (65.2 t/s), slower than GPT-5.5 (72.6 t/s) and Claude Sonnet 5 (102 t/s).

Artificial Analysis Indices
Medium
Intelligence38.2
Rank 71 of 790 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 & Accounting42.5
Rank 77 of 260 measured models
Strategy & Ops45.4
Rank 84 of 260 measured models
Legal40.5
Rank 90 of 260 measured models
Engineering42.6
Rank 60 of 259 measured models
Economics40.8
Rank 97 of 267 measured models
Standard Benchmarks
HLE40.2%
Rank 94 of 719 measured models
SciCode51.6%
Rank 111 of 286 measured models
AA-LCR80.7%
Rank 75 of 630 measured models
Terminal-Bench 4.032.3%
Rank 55 of 246 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