Long-context reasoning, strong coding and instruction following
7/9 done$1.213$0.015/pt
| Company | Moonshot AI |
|---|---|
| Family | — |
| Released | — |
| License | — |
| Parameters | — |
| Capabilities | Long-context reasoning, strong coding and instruction following |
| Task | Score | Status | Runtime | Tokens in | Tokens out | Cost |
|---|---|---|---|---|---|---|
| Equation Solver | 100.0 | success | 8.01s | 310 | 3,448 | $0.0071 |
| Mini Platformer | 100.0 platformer-jump1/1platformer-move1/1 | success | 1m 56s | 1,855 | 66,837 | $0.135 |
| Physics Pendulum Wave | 100.0 pendulum-renders1/1pendulum-animates1/1 | partial | 2m 36s | 1,840 | 97,639 | $0.196 |
| Crypto Hash Race | 96.4 | success | 15.98s | 305 | 8,139 | $0.016 |
| Circuit Builder Teaser | 87.0 circuit-structure1/1circuit-interact1/1 | success | 4m 08s | 1,830 | 126,021 | $0.253 |
| N-Body Field | 63.0 nbody-renders1/1nbody-animates0/1 | success | 4m 10s | 1,845 | 142,170 | $0.285 |
| Landing Page Morph | 35.0 landing-structure1/1landing-animates0/1 | partial | 5m 04s | 1,870 | 160,000 | $0.321 |