Back

OpenAI

GPT-6.1 Terra

Closed weights
Intelligence
33.5
Rank 118 of 759 measured models
Output speed
91.1 t/s
Rank 224 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
$0.107
Rank 56 of 211 measured models

GPT-6.1 Terra (Non-reasoning) scores 33.5 on the Artificial Analysis Intelligence Index, ranking 118th of 759 measured models. The closest models on this index are GLM-5.2 (33.7), Muse Spark 1.1 (Xhigh) (33.7), and Motif 3 (33.6). At $2 per million tokens (3:1 input/output blended price), it is cheaper than GLM-5.2 ($2.15), priced close to Muse Spark 1.1 (Xhigh) ($2). With an output speed of 91.1 t/s, it is about as fast as GLM-5.2 (94 t/s), slower than Muse Spark 1.1 (Xhigh) (283 t/s).

Artificial Analysis Indices
Non-reasoning
Intelligence33.5
Rank 118 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 & Accounting35.9
Rank 107 of 233 measured models
Strategy & Ops41.6
Rank 91 of 233 measured models
Legal35.1
Rank 110 of 233 measured models
Engineering32.4
Rank 113 of 232 measured models
Economics38.2
Rank 127 of 240 measured models
Standard Benchmarks
HLE21.1%
Rank 226 of 678 measured models
SciCode47.8%
Rank 138 of 245 measured models
AA-LCR67.7%
Rank 253 of 589 measured models
Terminal-Bench v426.8%
Rank 54 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