claude-sonnet-4.6

evaluated

Type: cloud

Capability starfish

green = capability (pass-rate) · blue = operational (vs roster) · dashed = roster average

Overall

mean domain rate

Solved

46/48

latest per bench

Gauntlet time

~5s/bench

Speed

23.8

tok/s

Steps/bench

1.7

decisiveness

$ / run

—

OpenRouter-equiv

Overall rank

#2 of 26

Agentic

#1 of 22

Coding

#1 of 22

Speed (tok/s)

#12 of 22

Decisive

#11 of 22

Strongest

Gate · 100%

Weakest

C# · 87%

Where it fits · live, recomputed from current results

#2 of 26 overall; strongest on Gate (100%); weakest on C# (87%); #12/22 for speed (23.8 tok/s). (auto-generated from current results)

Verdict history · snapshotted daily when it changes

2026-07-08#2 of 26 overall; strongest on Gate (100%); weakest on C# (87%); #12/22 for speed (23.8 tok/s). (auto-generated from current results)

2026-07-07#8 of 28 overall; strongest on Gate (100%); weakest on SupportFlow (33%); #11/25 on the supportflow gauntlet; #14/26 for speed (27.7 tok/s). (auto-generated from current results)

2026-07-06#23 of 28 overall; strongest on SupportFlow (47%); weakest on SupportFlow (47%); #7/24 on the supportflow gauntlet; #18/26 for speed (13.5 tok/s). (auto-generated from current results)

2026-07-04#23 of 28 overall; strongest on SupportFlow (47%); weakest on SupportFlow (47%); #7/23 on the supportflow gauntlet; #18/26 for speed (13.5 tok/s). (auto-generated from current results)

2026-07-03#22 of 28 overall; strongest on SupportFlow (47%); weakest on SupportFlow (47%); #7/22 on the supportflow gauntlet; #18/26 for speed (13.5 tok/s). (auto-generated from current results)

2026-07-02#21 of 30 overall; strongest on SupportFlow (47%); weakest on SupportFlow (47%); #6/26 on the supportflow gauntlet; #19/29 for speed (13.5 tok/s). (auto-generated from current results)

2026-07-01#17 of 28 overall; strongest on SupportFlow (58%); weakest on SupportFlow (58%); #3/23 on the supportflow gauntlet; #17/27 for speed (13.5 tok/s). (auto-generated from current results)

2026-06-30#16 of 28 overall; strongest on SupportFlow (58%); weakest on SupportFlow (58%); #3/21 on the supportflow gauntlet; #17/27 for speed (13.5 tok/s). (auto-generated from current results)

2026-06-29#15 of 28 overall; strongest on SupportFlow (58%); weakest on SupportFlow (58%); #3/21 on the supportflow gauntlet; #16/27 for speed (13.5 tok/s). (auto-generated from current results)

Domain breakdown

Gate

100%

11/11

Coding

100%

6/6

Agentic

100%

11/11

87%

13/15

PHP

100%

5/5

Benches run

green = passed · red = failed · hover for harness & time

Gate (11)

Coding (6)

Agentic (11)

C# (15)

PHP (5)

History (monthly pass-rate)

2026-07

54%

116/214

Availability record

When this model appeared in our catalogue census.

2026-06-25 · openrouter