Back

OpenAI

GPT-6.1 Terra

ReasoningOpen weightsModels.dev
Intelligence
48.1
Rank 26 of 759 measured models
Output speed
90.9 t/s
Rank 228 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
$0.404
Rank 111 of 211 measured models

GPT-6.1 Terra (Max) scores 48.1 on the Artificial Analysis Intelligence Index, ranking 26th of 759 measured models. The closest models on this index are Muse Spark 1.3 (48.1), GPT-6 Sol (47.6), and GPT-5.6 Sol (47.0). At $2 per million tokens (3:1 input/output blended price), it is cheaper than GPT-6 Sol ($4) and GPT-5.6 Sol ($8), priced close to Muse Spark 1.3 ($2). With an output speed of 90.9 t/s, it is faster than GPT-5.6 Sol (80.9 t/s), slower than Muse Spark 1.3 (176 t/s) and GPT-6 Sol (125 t/s).

Artificial Analysis Indices
Maximum
Intelligence48.1
Rank 26 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 & Accounting47.1
Rank 41 of 233 measured models
Strategy & Ops49.5
Rank 46 of 233 measured models
Legal49.0
Rank 45 of 233 measured models
Engineering49.1
Rank 28 of 232 measured models
Economics53.6
Rank 38 of 240 measured models
Standard Benchmarks
HLE46.2%
Rank 46 of 678 measured models
SciCode55.1%
Rank 54 of 245 measured models
AA-LCR82.7%
Rank 36 of 589 measured models
Terminal-Bench v455.6%
Rank 12 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