Touchstone
← Models

phi-4

Capability starfish
green = capability (pass-rate) · blue = operational (vs roster) · dashed = roster average
PHP5/5Speedn/aDecisiven/aCost-effn/a0
100%
Overall
mean domain rate
Solved
5/10
latest per bench
Gauntlet time
Speed
tok/s
Steps/bench
decisiveness
$ / run
OpenRouter-equiv
Overall rank
#1 of 26
Strongest
PHP · 100%
Weakest
PHP · 100%
Where it fits · live, recomputed from current results

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

Verdict history · snapshotted daily when it changes
2026-07-08#1 of 26 overall; strongest on PHP (100%); weakest on PHP (100%). (auto-generated from current results)
2026-07-03#2 of 28 overall; strongest on PHP (100%); weakest on PHP (100%). (auto-generated from current results)
2026-07-02#18 of 30 overall; strongest on PHP (100%); weakest on Agentic (11%); #20/29 for speed (13.3 tok/s). (auto-generated from current results)
2026-07-01#16 of 28 overall; strongest on PHP (100%); weakest on Agentic (11%); #18/27 for speed (13.3 tok/s). (auto-generated from current results)
2026-06-30#15 of 28 overall; strongest on PHP (100%); weakest on Agentic (11%); #18/27 for speed (13.3 tok/s). (auto-generated from current results)
2026-06-29#14 of 28 overall; strongest on PHP (100%); weakest on Agentic (11%); #17/27 for speed (13.3 tok/s). (auto-generated from current results)
Domain breakdown
PHP
100%
5/5
Benches run
green = passed · red = failed · hover for harness & time
PHP (5)
SWE (5)
History (monthly pass-rate)

No dated history yet.

Availability record
When this model appeared in our catalogue census.
2026-06-25 · openrouter2026-06-25 · openrouter