← Models
qwen3.6-27b
evaluatedVendor: Alibaba
Capability starfish
green = capability (pass-rate) · blue = operational (vs roster) · dashed = roster average
Overall
mean domain rate
Solved
85/90
latest per bench
Gauntlet time
29m
~34s/bench
Speed
7.8
tok/s
Steps/bench
1.5
decisiveness
$ / run
—
OpenRouter-equiv
Overall rank
#4 of 26Agentic
#9 of 22Coding
#9 of 22Speed (tok/s)
#19 of 22Decisive
#5 of 22Strongest
Gate · 100%Weakest
C# · 87%Where it fits · live, recomputed from current results
#4 of 26 overall; strongest on Gate (100%); weakest on C# (87%); #19/22 for speed (7.8 tok/s). (auto-generated from current results)
Verdict history · snapshotted daily when it changes
2026-07-08#4 of 26 overall; strongest on Gate (100%); weakest on C# (87%); #19/22 for speed (7.8 tok/s). (auto-generated from current results)
2026-07-07#3 of 28 overall; strongest on Gate (100%); weakest on SupportFlow (84%); #2/25 on the supportflow gauntlet; #21/26 for speed (7.5 tok/s). (auto-generated from current results)
2026-07-06#3 of 28 overall; strongest on Gate (100%); weakest on SupportFlow (83%); #2/24 on the supportflow gauntlet; #21/26 for speed (7.5 tok/s). (auto-generated from current results)
2026-07-05#7 of 28 overall; strongest on Gate (100%); weakest on Coding (83%); #2/23 on the supportflow gauntlet; #21/26 for speed (7.5 tok/s). (auto-generated from current results)
2026-07-04#7 of 28 overall; strongest on Gate (100%); weakest on SupportFlow (79%); #2/23 on the supportflow gauntlet; #21/26 for speed (7.6 tok/s). (auto-generated from current results)
2026-07-03#7 of 28 overall; strongest on Gate (100%); weakest on SupportFlow (79%); #2/22 on the supportflow gauntlet; #21/26 for speed (7.6 tok/s). (auto-generated from current results)
2026-07-02#13 of 30 overall; strongest on Gate (100%); weakest on C# (47%); #2/26 on the supportflow gauntlet; #23/29 for speed (7.6 tok/s). (auto-generated from current results)
Domain breakdown
Gate
100%
22/22
Coding
100%
12/12
Agentic
94%
15/16
C#
87%
26/30
PHP
100%
10/10
Benches run
green = passed · red = failed · hover for harness & time
Gate (22)
Coding (12)
Agentic (16)
C# (30)
PHP (10)
History (monthly pass-rate)
2026-07
95%
317/334
Availability record
When this model appeared in our catalogue census.
2026-06-25 · openrouter