Back

OpenAI

GPT-6.1 Terra

ReasoningClosed weights
Intelligence
43.9
Rank 48 of 759 measured models
Output speed
91 t/s
Rank 225 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
$0.134
Rank 69 of 211 measured models

GPT-6.1 Terra (High) scores 43.9 on the Artificial Analysis Intelligence Index, ranking 48th of 759 measured models. The closest models on this index are Ling 3.1 Flash 1019 (43.9), Step 5 Preview (43.7), and Kimi K3 (43.6). At $2 per million tokens (3:1 input/output blended price), it is cheaper than Kimi K3 ($6), more expensive than Ling 3.1 Flash 1019 ($0.45) and Step 5 Preview ($1.43). With an output speed of 91 t/s, it is faster than Kimi K3 (54.8 t/s), slower than Step 5 Preview (192 t/s).

Artificial Analysis Indices
High
Intelligence43.9
Rank 48 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 & Accounting43.9
Rank 64 of 233 measured models
Strategy & Ops47.0
Rank 63 of 233 measured models
Legal47.0
Rank 56 of 233 measured models
Engineering44.7
Rank 48 of 232 measured models
Economics50.6
Rank 58 of 240 measured models
Standard Benchmarks
HLE43.3%
Rank 62 of 678 measured models
SciCode51.6%
Rank 98 of 245 measured models
AA-LCR82.3%
Rank 42 of 589 measured models
Terminal-Bench v441.9%
Rank 31 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