Kimi-Linear-48B-A3B-Instruct
Kimi-Linear-48B-A3B-Instruct.
3
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Moonshot AI Oct 2025
Kimi-Linear-48B-A3B-Instruct
Open weights Mid-size
No Epoch Capabilities Index score yet
- Terminal-Bench Pro 0.05% #23 /23
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 15 | #185 of 201 | Official leaderboard | |
| Dubesor AI Chess Leaderboard | 489 | #240 of 250 | Official leaderboard | |
| Terminal-Bench Pro | 0.05% | #23 of 23 | Official leaderboard |
What does it cost to run?
On the 2 leaderboards that publish a price, its best run usually costs about 1/6 of the median model's. On every one, another model comes close to its score for less.
| Benchmark | Score | Price | From cheapest to priciest | Against the median | Close to its score for less Close for less |
|---|---|---|---|---|---|
| Dubesor AI Chess Leaderboard | 489 | $0.03 0.1× the median | 0.1× | | |
| SnakeBench | 15 | $0.0091 0.2× the median | 0.2× | |
Who measured it?
Independent runs cover all 3 of its benchmarks.
- An independent run only 3
Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards