Back

Trillion Labs

Tri-21B-Think

ReasoningOpen weights
Intelligence
9.0
Rank 462 of 744 measured models
Context window
32K
Rank 1065 of 1199 measured models

Tri-21B-Think scores 9.0 on the Artificial Analysis Intelligence Index, ranking 462nd of 744 measured models. The closest models on this index are Granite 4.2 3B (9.1), Devstral Medium (9.0), and GPT-4o (March 2025, chatgpt-4o-latest) (9.0).

Artificial Analysis Indices
Intelligence9.0
Rank 462 of 744 measured models
Standard Benchmarks
GPQA Diamond60.1%
Rank 405 of 619 measured models
HLE5.9%
Rank 431 of 664 measured models
IFBench54.6%
Rank 155 of 450 measured models
AA-LCR15.7%
Rank 469 of 575 measured models
TerminalBench Hard0.8%
Rank 370 of 432 measured models
τ²-Bench81.0%
Rank 125 of 440 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