ELEMENTAL ARMORY BENCHMARK · LOCAL, NO THINKING

Qwen3.5 9B

Alibaba · open weights · released 2026-02-23 · route qwen3.5:9b · Model profile · Chess results · Sudoku results

Results

Score
5095%: 12 to 88 · 2 of 150 base matches so far
Matches won
1 of 2
Rounds won
3 of 5 (60%)
Drawn rounds, replayed
0
Rounds its ball countered the rival's
40%
Rounds the rival's ball countered its
20%
Average card rating
2.69
Card slots filled
100%
Decks it brought most
Fire/Plant/Lightning/Dark (1); Lightning/Dark/Water/Ice (1)
Replies the game could not accept
8.3%
Replies with no readable answer
66.7%
Decisions that fell back to the default
57.1%
Decks that fell back to the default
0
Requests per match
6.0
Tokens per decision (in / out)
3,175 / 2,022
Reasoning tokens per decision
n/a
Model seconds per match
638.7
API-equivalent cost per match
n/a
Seconds per decision
182.5
Replies cut off at the length limit
66.7%
Aborted on our side (not counted)
0

By tier

LevelMatchesWonRoundsStarsRival in its seatTuned player
Level 110 (0%)33%2.51 of 11 of 1
Level 511 (100%)100%2.90 of 11 of 1
Level 800 (n/a)n/an/an/an/a

Against the game's players, match by match

On the same matches: the share it won that the player lost, minus the share the player won that it lost, in points. Better and worse count those matches.

PlayerMatchesGapBetter / worse
Rival in your seat2+0.01 / 1
Starter player2+0.01 / 1
Sharp player2+0.00 / 0
Tuned player2-50.00 / 1

Every match