← Evals

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.

• multi-llm-servers · 2b11b97 72% 13/18 49%–88%

Against another eval of the same questions

backend edge backend edge-thanveer main bdd945f six multi-llm main

Within noise: a difference this size could easily be chance with 18 and 12 runs. Fisher's exact test, two-sided, p = 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.

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 49
• no equation determines the … from what is known 45
• undefined method '…' for an instance of Physics::PhysicalObject 18
• ArgumentError 17
• gives nothing called … 14
• deduces from “…%{…”, which it never says 12
• which the solution's laws leave out…; or take one 9
• gives … but never says where in what it asks 5
• 5 other categories 10

• multi-llm-servers · 2b11b97 179 in 18 runs

Most frequent errors

1. 23ArgumentErrorArgumentError: wrong number of arguments (given 0, expected 1)
2. 23no equation determines the … from what is knownRuntimeError: no equation determines the time taken of stopping from what is known
3. 21no equation determines the … from what is knownRuntimeError: no equation determines the force on a wire on a from what is known
4. 16no equation determines the … from what is knownRuntimeError: no equation determines the mass of ice from what is known
5. 13no equation determines the … from what is knownRuntimeError: no equation determines the force on a wire on wire a from what is known
6. 11which the solution's laws leave out…; or take oneNoMethodError: undefined method 'separation' for an instance of Physics::PhysicalObject; separation is a quantity of CoulombsLaw, ElectricField, TravellingWave, which the solution's laws leave out (add one to using:), not a method: reach it from an object, as <object>.separation, qualified as needed by from: <object>; or take one the solution's laws already name for that kind of quantity: radius, length_of_the_coil, distance_from_the_wire
7. 10undefined method '…' for an instance of Physics::PhysicalObjectNoMethodError: 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
8. 7deduces from “…%{…”, which it never saysArgumentError: copper_block_on_ice deduces from “heat of fusion of water = %{fusion}”, which it never says
9. 7undefined method '…' for an instance of Physics::PhysicalObjectNoMethodError: undefined method 'distance_from' for an instance of Physics::PhysicalObject; did you mean <object>.distance_from_the_wire?
10. 7gives nothing called …ArgumentError: two_parallel_wires gives nothing called length
11. 5gives … but never says where in what it asksArgumentError: a_whirled_stone gives turns but never says where in what it asks
12. 5deduces from “…%{…”, which it never saysArgumentError: two_parallel_wires deduces from “separated by a distance of %{separation}”, which it never says

Where it ran

• agent 17b9257 · engine 453fb0d

  machine

  omarchy

  worktree

  /home/fazzledev/Work/phryzby-app--multi-llm-servers

  commit

  2b11b97 on multi-llm-servers

  clean

  yes

  ruby · rails

  3.4.7 · 8.1.4

  llm server

  edge · http://10.8.0.2:8080 · 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, 81% → on mains, 65%

  time

  14 Oct 02:46 → 14 Oct 02:54

• agent 17b9257 · engine 453fb0d

  machine

  omarchy

  worktree

  /home/fazzledev/Work/phryzby-app--multi-llm-servers

  commit

  2b11b97 on multi-llm-servers

  clean

  yes

  ruby · rails

  3.4.7 · 8.1.4

  llm server

  edge · http://10.8.0.2:8080 · 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, 65% → on mains, 58%

  time

  14 Oct 02:54 → 14 Oct 03:05

• agent 17b9257 · engine 453fb0d

  machine

  omarchy

  worktree

  /home/fazzledev/Work/phryzby-app--multi-llm-servers

  commit

  2b11b97 on multi-llm-servers

  clean

  yes

  ruby · rails

  3.4.7 · 8.1.4

  llm server

  edge · http://10.8.0.2:8080 · 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, 58% → on mains, 40%

  time

  14 Oct 03:05 → 14 Oct 03:32