Back

Trillion Labs

Tri-21B-think Preview

ReasoningOpen weights
Intelligence
9.6
Rank 437 of 744 measured models
Context window
32K
Rank 1065 of 1199 measured models

Tri-21B-think Preview scores 9.6 on the Artificial Analysis Intelligence Index, ranking 437th of 744 measured models. The closest models on this index are DeepSeek V3 0324 (9.7), GPT-4.5 (Preview) (9.6), and Qwen3 Coder 30B A3B Instruct (9.6).

Artificial Analysis Indices
Intelligence9.6
Rank 437 of 744 measured models
Standard Benchmarks
GPQA Diamond53.8%
Rank 448 of 619 measured models
HLE5.8%
Rank 435 of 664 measured models
IFBench47.1%
Rank 201 of 450 measured models
AA-LCR21.7%
Rank 440 of 575 measured models
TerminalBench Hard2.3%
Rank 338 of 432 measured models
τ²-Bench93.3%
Rank 44 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