Tiny Recursion Model (TRM): benchmark scores, price and ranking
Tiny Recursion Model (TRM) ranks #403 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.8), based on 1 benchmark results captured up to 2026-10-13.
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Aggregate rank
- #403 of 743 (score 47.8)
Across the 1 benchmark where at least ten models are scored, Tiny Recursion Model (TRM) is in the top 10% on 0 and in the top half on 0.
Tiny Recursion Model (TRM) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| ARC-AGI-2 | 6.2% | #54 of 87 | ARC Prize official leaderboard | 2026-10-13 |
About Tiny Recursion Model (TRM)
Tiny Recursion Model (TRM) is a smaller, lower-cost model. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Tiny Recursion Model (TRM) stands
On our aggregate score, Tiny Recursion Model (TRM) is #403 of 743 ranked models, around the middle of the table. Its score is 47.8; the scale is centred on 50, so it sits 2.2 points below the typical model. That beats 46% of the ranked field.
Tiny Recursion Model (TRM), benchmark by benchmark
Tiny Recursion Model (TRM) lands below the middle on ARC-AGI-2: 6.2%, #54 of 87, with 61% of the field scoring higher. GPT-6 Astra (max) leads at 95.0%; the closest result above is o3 (high) at 6.5%. It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so Tiny Recursion Model (TRM) is 16.5 points below it. Source: ARC Prize official leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: ARC Prize official leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #400 gemini-2.0-flash-thinking-exp-01-21 (47.9)
- #401 Kimi K2 Thinking (47.8)
- #402 GPT-5.1 (Thinking, Medium) (47.8)
- #404 DeepSeek-V2-Chat (47.8)
- #405 Muse Code + Muse Spark 1.3 (47.8)
- #406 DeepSeek-V3.2 (47.7)
Compare it on the live leaderboard → · How the aggregate score works