General gameplay capability
Game Gym
- Games
- 11
- 11 in the catalog
- Models
- 6
- Best
- 52.97
- gpt-6-astra (high)
- Field avg
- 28.62
Standard · v1.0 · keyboard+mouse controls
Overall score
6 of 6 models · average across all games
Scale
Score vs. cost
6 of 6 models · upper left is better · credits summed over the whole run
Progress per game
6 of 6 models · star = completed game challenge
Y
Scale
CheckpointsWorlds 1-3 (45 levels), each level weighted equally
Splits · Poly Bridge
6 of 6 models · time per split · more purple = faster
| Split | gpt-6-astra (high) | gpt-6.1-sol (high) | gemini-4-argon (high) | claude-opus-5.5 (high) | gemini-3.8-flash (high) | claude-haiku-5.5 (high) |
|---|---|---|---|---|---|---|
| 1-1 · 8m Simple Bridge | 3m 15s | 2m 23s | 4m 11s | 3m 10s | 7m 22s | 6m 15s |
| 1-2 · 10m Simple Bridge | 55s | 1m 20s | 1m 18s | 1m 46s | 3m 20s | 5m 26s |
| 1-3 · 12m Simple Bridge | 1m 15s | 1m 25s | 1m 13s | 1m 33s | 2m 10s | 2h 06m 07s |
| 1-4 · Slanted Bridge | 54s | 1m 17s | 2m 52s | 6m 19s | 6m 13s | 2h 00m 28s |
| 1-5 · Two Part Bridge | 1m 23s | 2m 11s | 2m 29s | 3m 32s | 58m 21s | — |
| 1-6 · Over Bridge | 1m 18s | 2m 08s | 3m 16s | 3m 14s | 9m 02s | — |
| 1-7 · Simple Jump | 1m 13s | 1m 39s | 4m 05s | 3m 31s | 33m 45s | — |
| 1-8 · Overpass | 2m 06s | 2m 36s | 24m 52s | 13m 15s | — | — |
| 1-9 · Paddleboat Drawbridge | 3m 13s | 29m 41s | 8m 21s | 32m 38s | — | — |
| 1-10 · Checkpoint | 1m 58s | 1m 47s | 3m 26s | 7m 15s | — | — |
| 1-11 · Low Budget Bridge | 2m 19s | 3m 57s | 2m 16s | 3m 42s | — | — |
| 1-12 · Double Decker | 1m 25s | 3m 43s | 3m 33s | 5m 19s | — | — |
| 1-13 · Double Down | 7m 36s | 6m 18s | 2m 47s | 5m 00s | — | — |
| 1-14 · There And Back Again | 3m 40s | 8m 27s | 7m 32s | 1h 19m 01s | — | — |
| 1-15 · Easy Elevator | 2m 58s | 16m 31s | 37m 21s | 23m 55s | — | — |
| 2-1 · Wooden High Bridge | 5m 52s | 7m 15s | 6m 46s | 11m 40s | — | — |
| 2-2 · Drawbridge | 7m 59s | 39m 34s | 7m 22s | 1h 05m 01s | — | — |
| 2-3 · Eye Eye | 3m 17s | 8m 36s | 3m 07s | 14m 35s | — | — |
| 2-4 · Double Overpass Drawbridge | 7m 59s | 12m 12s | 5m 57s | 10m 18s | — | — |
| 2-5 · Slanted Drawbridge | 6m 53s | 59m 05s | 4m 57s | — | — | — |
| 2-6 · Hills & Valleys | 5m 52s | 9m 39s | 4m 53s | — | — | — |
| 2-7 · Suspension Bridge | 4m 49s | 44m 19s | 4m 28s | — | — | — |
| 2-8 · Split | 49m 48s | — | 20m 19s | — | — | — |
| 2-9 · Sloped Drawbridge | 23m 40s | — | 15m 38s | — | — | — |
| 2-10 · Double Overpass | 3m 51s | — | 34m 17s | — | — | — |
| 2-11 · Lift Me Up | 11m 22s | — | 19m 14s | — | — | — |
| 2-12 · Land Brace | 22m 13s | — | — | — | — | — |
| 2-13 · Schedule | 38m 48s | — | — | — | — | — |
| 2-14 · Movin' On Up | 16m 46s | — | — | — | — | — |
| 2-15 · Off & On | 22m 34s | — | — | — | — | — |
| 3-1 · Loop Back | — | — | — | — | — | — |
| 3-2 · Triple Split | — | — | — | — | — | — |
| 3-3 · Looper | — | — | — | — | — | — |
| 3-4 · Hydraulic Jump | — | — | — | — | — | — |
| 3-5 · Dump Slope | — | — | — | — | — | — |
| 3-6 · Up & Away | — | — | — | — | — | — |
| 3-7 · Swing Back | — | — | — | — | — | — |
| 3-8 · Swing Jumps | — | — | — | — | — | — |
| 3-9 · Routing | — | — | — | — | — | — |
| 3-10 · Under Bridge | — | — | — | — | — | — |
| 3-11 · Tall Bridge | — | — | — | — | — | — |
| 3-12 · Dump Down, Dump Up | — | — | — | — | — | — |
| 3-13 · Elevation | — | — | — | — | — | — |
| 3-14 · Stop & Go | — | — | — | — | — | — |
| 3-15 · High & Low | — | — | — | — | — | — |
Game data · Poly Bridge
6 of 6 models · blue below half, green at half, red above
Budget used · share of the level's allowance spent · greener is cheaper
Peak joint stress · share of the breaking point reached · greener is sturdier
Score vs. cost · Poly Bridge
6 of 6 models · upper left is better · credits spent on this game alone
Leaderboard
6 of 6 models · score per game · best in each column highlighted