pr72 v4 main rerun 1
only: pushed_two_ways, how_long_to_stop, a_stone_on_a_string, and caesium_s_stopping_potential. 1 run per question, started 14 Oct 15:09, finished 14 Oct 15:12.
done
Solve rate
Solved runs out of all runs for each agent version, with a 95% Wilson interval. Runs cut short by the machine (a killed process, the LLM server unreachable, the engine timing out) are left out.
- bd007a8 50% 2/4 15%–85%
Against another eval of the same questions
pr72 v4 branch rerun 1 pr72 v4 branch rerun 2 pr72 v4 branch rerun 3 pr72 v4 main rerun 2 pr72 v4 main rerun 3
Within noise: a difference this size could easily be chance with 4 and 4 runs. Fisher's exact test, two-sided, p = 1.0.
| question | pr72 v4 main rerun 1 | pr72 v4 branch rerun 2 | difference | p |
|---|---|---|---|---|
| pushed_two_ways | 0/1 | 1/1 | +100 pts | 1.0 |
| how_long_to_stop | 1/1 | 0/1 | -100 pts | 1.0 |
| a_stone_on_a_string | 0/1 | 0/1 | +0 pts | 1.0 |
| caesium_s_stopping_potential | 1/1 | 1/1 | +0 pts | 1.0 |
| overall | 2/4 | 2/4 | +0 pts | 1.0 |
Tokens and time
Medians per run. Tokens come from RubyLLM's usage records; tokens per second is completion tokens over the run's wall time.
| version | prompt tokens | completion tokens | tokens/s | wall time | time per check |
|---|---|---|---|---|---|
| bd007a8 | 23,808 | 3,848 | 83.7 | 52 s | 3.0 s |
Every run
One dot per run, green solved, red stuck and grey interrupted, larger for more rounds; a hollow dot has no checks recorded. Hover or tap a dot for its top errors, and open it for the question's page.
Why checks fail
Each version's failed checks, as shares of the whole, by the hint in Question::HINTS their error matches first, or by the error's class when no hint matches. A check that repeats the error before it, in a streak of 3 or more, counts as a repeated failing move.
- repeated failing move 0
- which none of its laws name/give to anything 21
- undefined method '…' for an instance of Physics::PhysicalObject 11
- undefined local variable or method '…' for an instance of Physics::Solving 9
- ArgumentError 5
- no equation determines the … from what is known 4
- is a word Ruby already uses 2
- NoMethodError 1
- 3 other categories 3
- bd007a8 56 in 4 runs
As a table
| category | bd007a8 |
|---|---|
| repeated failing move | 0 |
| which none of its laws name/give to anything | 21 |
| undefined method '…' for an instance of Physics::PhysicalObject | 11 |
| undefined local variable or method '…' for an instance of Physics::Solving | 9 |
| ArgumentError | 5 |
| no equation determines the … from what is known | 4 |
| is a word Ruby already uses | 2 |
| NoMethodError | 1 |
| SyntaxError | 1 |
| gives nothing called … | 1 |
| gives … but never says where in what it asks | 1 |
Most frequent errors
- 11undefined method '…' for an instance of Physics::PhysicalObject
NoMethodError: undefined method 'time_taken' for an instance of Physics::PhysicalObject; time_taken is a quantity of Velocity, through UniformCircularMotion, not a method: reach it from a motion, as <motion>.time_taken - 9undefined local variable or method '…' for an instance of Physics::Solving
NameError: undefined local variable or method 'stone_motion' for an instance of Physics::Solving - 3no equation determines the … from what is known
RuntimeError: no equation determines the time taken of braking from what is known - 2ArgumentError
ArgumentError: two_forces_at_right_angles gives the force on body by pusher1 during pushed twice: 8 N and 8 N - 2is a word Ruby already uses
ArgumentError: round is a word Ruby already uses: call it something else - 1ArgumentError
ArgumentError: car_braking_to_rest gives the velocity of car at end of braking from ground twice: 0 m/s and 0 m/s - 1gives … but never says where in what it asks
ArgumentError: a_whirled_stone gives turns but never says where in what it asks - 1which none of its laws name/give to anything
NameError: two_forces_at_right_angles chooses a root of #<struct Physics::Pointing size=#<Physics::Whole:0x00007dc472275920 @name=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>, @written=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>>>, which none of its laws name - 1NoMethodError
NoMethodError: undefined method 'along' for an instance of Physics::Whole - 1which none of its laws name/give to anything
NameError: a_whirled_stone takes acceleration as centripetal acceleration of stone, which none of its laws name - 1which none of its laws name/give to anything
NameError: two_forces_at_right_angles chooses a root of #<struct Physics::Pointing size=#<Physics::Whole:0x000079d77f9abae8 @name=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>, @written=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>>>, which none of its laws name - 1which none of its laws name/give to anything
NameError: two_forces_at_right_angles chooses a root of #<struct Physics::Pointing size=#<Physics::Whole:0x000075f7c61add88 @name=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pusher1: "p1", pusher2: "p2", pushed: ""}>, @written=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pusher1: "p1", pusher2: "p2", pushed: ""}>>>, which none of its laws name
Where it ran
-
agent
17b9257· engine453fb0d- machine
- omarchy
- worktree
- /home/fazzledev/Work/phryzby-app--pr72-main-eval
- commit
- bd007a8 on HEAD
- clean
- yes
- ruby · rails
- 3.4.7 · 8.1.4
- llm server
- edge-thanveer · http://127.0.0.1:8083 · llama.cpp b11371-99b95488c
- model
- qwen3.5:9b · Q4_K_M · 49152 context
- gpu
- Advanced Micro Devices, Inc. [AMD/ATI] Navi 33 [Radeon RX 7600/7600 XT/7600M XT/7600S/7700S / PRO W7600] (rev c1); Advanced Micro Devices, Inc. [AMD/ATI] Phoenix1 (rev c2)
- power
- on mains, 79% → on mains, 79%
- time
- 14 Oct 15:09 → 14 Oct 15:12