Compare

Model vs model

Pick up to 4 models, at one effort or their best, and see them side by side: the Index and every test, level by level on the same cubes, moves, time, tokens, cost, how effort changes them, and the coding benchmark. Every chart and card downloads as an image.

Claude Opus 5

Anthropic · max effort Verified

Fast Index
35.0#14 of 64
Thorough
–not run
Coding
–not run
Moves / solve
721 cubes solved
Cost (Fast)
$716h 43m

Head to head

Every measure side by side; the best on each row is marked. Averages where an effort was run more than once.

MeasureClaude Opus 5 (max)
Rows won0
Fast suite
Fast Index35.0
Rank on the Fast Index#14 of 64
4×4 GauntletGauntlet locked
2×2 ladder, interactive100 · L11/11
3×3 ladder, interactive25.0 · L5/20
3×3 ladder, one-shot25.0 · L5/20
Cubes solved21
Moves on the shared cubes–
Moves per cube solved7
Time6h 43m
Input tokens5.5M
Output tokens2.2M
Cost$71
Cost per Index point$2.02
Minutes per Index point11.5
Runs averaged1

Costs marked * are estimated from tokens at list prices. Ties share the mark.

Fast, test by test

Each test out of 100. The Index weighs the 2×2 ladder 20% and each 3×3 ladder 30%. A perfect 100 on all three unlocks the 4×4 Gauntlet: two 4×4 ladders of 20 levels, worth 10% each. Without it, 80 is the top score.

Fast Index

Claude Opus 5 (max)35.0

2×2 ladder, interactive

Claude Opus 5 (max)100

3×3 ladder, interactive

Claude Opus 5 (max)25.0

3×3 ladder, one-shot

Claude Opus 5 (max)25.0

Level by level

Every level of each ladder, from each model's best run. The number is the moves it took; red marks are missed tries. Everyone gets the same cube on a level's first try, so the fewest moves there is starred. Click a level for its replay.

2×2 ladder, interactive

1234567891011Score
Claude Opus 5max123457718291823100

3×3 ladder, interactive

1234567891011121314151617181920Score
Claude Opus 5max12345✕25.0

3×3 ladder, one-shot

1234567891011121314151617181920Score
Claude Opus 5max12345✕25.0
  • solved first try
  • solved after a miss
  • missed, the ladder ended
  • not reached

Does more effort help?

The Fast Index at every effort each model has been run at, whichever effort is picked above.

  • Claude Opus 5

Claude Opus 5 · The Index · Coding board