Touchstone
← Models

Qwen3-235B-A22B (cluster)

shelved
Params: 235B-A22BQuant: Q4Type: local
Capability starfish
green = capability (pass-rate) · blue = operational (vs roster) · dashed = roster average
C#12/15PHP5/5Speedn/aDecisiven/aCost-effn/a0
90%
Overall
mean domain rate
Solved
17/20
latest per bench
Gauntlet time
Speed
tok/s
Steps/bench
decisiveness
$ / run
OpenRouter-equiv
Overall rank
#10 of 26
Strongest
PHP · 100%
Weakest
C# · 80%
Where it fits · live, recomputed from current results

#10 of 26 overall; strongest on PHP (100%); weakest on C# (80%). (auto-generated from current results)

Audit — why not run further: Q4 yardstick only; dense 235B too slow on cluster, full run would time out. Cluster retired.

Verdict history · snapshotted daily when it changes
2026-07-09#10 of 26 overall; strongest on PHP (100%); weakest on C# (80%). (auto-generated from current results)
2026-07-08#11 of 26 overall; strongest on PHP (100%); weakest on C# (80%). (auto-generated from current results)
2026-07-07#19 of 28 overall; strongest on PHP (100%); weakest on SupportFlow (28%); #13/25 on the supportflow gauntlet; #24/26 for speed (5.3 tok/s). (auto-generated from current results)
2026-07-06#18 of 28 overall; strongest on PHP (100%); weakest on SupportFlow (28%); #13/24 on the supportflow gauntlet; #24/26 for speed (5.3 tok/s). (auto-generated from current results)
2026-07-05#18 of 28 overall; strongest on PHP (100%); weakest on SupportFlow (28%); #14/23 on the supportflow gauntlet; #23/26 for speed (5.3 tok/s). (auto-generated from current results)
2026-07-04#18 of 28 overall; strongest on PHP (100%); weakest on SupportFlow (28%); #13/23 on the supportflow gauntlet; #23/26 for speed (5.3 tok/s). (auto-generated from current results)
2026-07-03#18 of 28 overall; strongest on PHP (100%); weakest on SupportFlow (28%); #12/22 on the supportflow gauntlet; #23/26 for speed (5.3 tok/s). (auto-generated from current results)
2026-07-02#14 of 30 overall; strongest on PHP (100%); weakest on SupportFlow (28%); #13/26 on the supportflow gauntlet; #25/29 for speed (5.3 tok/s). (auto-generated from current results)
2026-07-01#13 of 28 overall; strongest on Gate (100%); weakest on SupportFlow (15%); #15/23 on the supportflow gauntlet; #22/27 for speed (7.5 tok/s). (auto-generated from current results)
2026-06-30#23 of 28 overall; strongest on SupportFlow (5%); weakest on SupportFlow (5%); #16/21 on the supportflow gauntlet; #22/27 for speed (6.8 tok/s). (auto-generated from current results)
Domain breakdown
C#
80%
12/15
PHP
100%
5/5
Benches run
green = passed · red = failed · hover for harness & time
C# (15)
PHP (5)
History (monthly pass-rate)

No dated history yet.

Availability record
When this model appeared in our catalogue census.

No census snapshots recorded yet.