← Back to home
The scoreboard

Final scores:
Amp vs Claude

Two experiments, one verdict. In the quantum benchmark the harness varies and so does the model; in the baboons game the model is held constant so the gap is pure harness. Either way, the better harness wins on time and cost at equal-or-better quality.

🏆
Amp — Quantum
1.000 correctness · $1.93 · ~24× faster · ~39× cheaper
🏆
Amp — Baboons (process)
2.1× faster · 2.6× cheaper · you judge the game itself
Experiment 01 · quantum-compilation optimization

Quantum benchmark — final scores

Amp rush (fast mode) vs Claude Code + Claude Fable 5 at max effort, on 4 hard C++ tasks both agents completed. Warm iterative, 3 iterations, hidden weighted target tests compiled with g++.

1.000
Amp correctness
0.972
Claude correctness
$1.93
Amp total cost
$75.40
Claude total (+1 timeout)
TaskAmp rewardAmp $totAmp avg sClaude rewardClaude $totClaude avg sCost ratio
cpp-qmap · qubit routing (NP-complete)1.000$0.46590.889$28.741,48962×
cpp-pulse · GRAPE control1.000$0.42491.000$13.96 +TO1,33533×
cpp-ftsched · magic-state1.000$0.57401.000$12.5388722×
cpp-jsonmini · JSON parser1.000$0.48461.000$20.171,01342×
All 4 (mean / total)1.000$1.93490.972$75.401,18139×

Across these 4 tasks Amp rush was ~39× cheaper and ~24× faster per iteration at equal-or-better correctness. On the full 8-task suite Claude only completed 4 (a monthly spend limit blocked the rest), giving completion scores of 1.000 (Amp) vs 0.486 (Claude). No agent used assembly, though both were allowed to.

Experiment 03 · same model, pure harness

Baboons game — final scores

Both agents ran the identical prompt on the identical model (Claude Fable 5). The only variable is the harness: Amp vs Claude Code. 3 cold runs each.

453.8 s
Amp avg duration
953.3 s
Claude avg duration
$2.65
Amp avg cost / run
$6.95
Claude avg cost / run
RunAmp durationAmp costAmp LOCClaude durationClaude costClaude LOC
Cold 1397.1 s$2.931,118765.4 s$4.801,253
Cold 2547.6 s$2.601,1501,107.9 s$8.841,170
Cold 3416.5 s$2.421,218986.6 s$7.201,196
Average453.8 s$2.651,162953.3 s$6.951,206
3-run total$7.95$20.84 — exhausted the Claude Max monthly limit

Same model → these gaps are pure harness: Amp ~2.1× faster and ~2.6× cheaper. Output size was similar (~1,100–1,200 LOC) — more lines is not a better game, so the game verdict is left to you.

Bottom line

The harness carried the outcome.

Whether the model changed (quantum) or stayed fixed (baboons), the better-engineered agent finished faster, cost far less, and matched or beat correctness. The model is the engine — but the harness is the car.

← Back to home