# We ran 2 vs 4 agents six times. Four agents cost 2.1 and did not improve success

> Source: <https://dev.to/janzong/we-ran-2-vs-4-agents-six-times-four-agents-cost-21x-and-did-not-improve-success-k98>
> Published: 2026-09-22 21:51:04+00:00

**Short version:** I ran a preregistered 2-agent versus 4-agent comparison on a deterministic task.

Six live runs completed under hard caps. Both groups succeeded in exactly one of three repeats.

The 4-agent group cost **2.115×** more per run and per complete success. More agents were operationally

viable; they were not better on this task.

The scenario is a deterministic public-repair contribution task:

The point of forcing coverage was to avoid the earlier failure mode where one agent dominated every

turn and the other participants never acted.

| Item | Value | 
|---|---|
| Groups | 2 agents / 3 steps; 4 agents / 5 steps | 
| Repeats | 3 per group | 
| Caps per run | 150 calls / USD 0.50 / 600s | 
| Choice model | `deepseek-flash` on a Responses API contract | 
| Outcome | machine-decidable `outcome.json` | 
| Validity | provenance, coverage, integer choices, arithmetic, caps, port closure, archive hashes | 

All six runs passed every validity gate. No parser failure, no budget breach, no port leak.

| Run | Agents | Total / threshold | Success | Zero contributors | Calls | Total tokens | Cost USD | 
|---|---|---|---|---|---|---|---|
| 2-agent r1 | 2 | 2 / 3 | no | 1 | 17 | 10,060 | 0.0269116 | 
| 2-agent r2 | 2 | 3 / 3 | yes | 0 | 17 | 11,070 | 0.0313716 | 
| 2-agent r3 | 2 | 0 / 3 | no | 2 | 17 | 10,255 | 0.0281116 | 
| 4-agent r1 | 4 | 3 / 5 | no | 2 | 33 | 21,493 | 0.0597772 | 
| 4-agent r2 | 4 | 2 / 5 | no | 2 | 33 | 22,679 | 0.0641372 | 
| 4-agent r3 | 4 | 5 / 5 | yes | 0 | 33 | 21,459 | 0.0588042 | 

Group aggregates:

| Metric | 2-agent | 4-agent | Ratio | 
|---|---|---|---|
| complete successes | 1 / 3 | 1 / 3 | 1.000 | 
| mean calls | 17.00 | 33.00 | 1.941 | 
| mean total tokens | 10,461.67 | 21,877.00 | 2.091 | 
| mean cost USD | 0.028798 | 0.060906 | 2.115 | 
| mean zero contributors | 1.000 | 1.333 | 1.333 | 

Two pieces are now public:

`6cc70156facb37baf23fe5fe57dad93d43502b91`) — schema, synthetic GenMentor adapter, fixtures, tests;` v0.1.0-rc2`) — local-first run validation, hashed reports, and a synthetic deletion proof.
The full protocol and the archived runs stay private. The result is intentionally boring: a negative result with caps, hashes, and every failed run preserved.

I am also looking for **three independent reproductions by non-authors**. The trust layer guide expects `13 passed` under both `TZ=UTC` and `TZ=Asia/Shanghai`, `report_hash` `a841b192981fd7e7`, and deletion `audit_hash` `4f0193abbd49a0f9`. If you run it and any hash differs, that is the most useful reply I can get. If you have a task where you believe more agents should win, that is the experiment I want to run next.