Pop quiz: what's wrong with measureWrong()?

IterationBenchmark.java

package org.sample;

import org.openjdk.jmh.annotations.BenchmarkMode;
import org.openjdk.jmh.annotations.Fork;
import org.openjdk.jmh.annotations.GenerateMicroBenchmark;
import org.openjdk.jmh.annotations.Measurement;
import org.openjdk.jmh.annotations.Mode;
import org.openjdk.jmh.annotations.OutputTimeUnit;
import org.openjdk.jmh.annotations.Param;
import org.openjdk.jmh.annotations.Scope;
import org.openjdk.jmh.annotations.Setup;
import org.openjdk.jmh.annotations.State;
import org.openjdk.jmh.annotations.Warmup;
import org.openjdk.jmh.logic.BlackHole;

import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.TimeUnit;

@Measurement(iterations = 5)
@Warmup(iterations = 5)
@Fork(3)
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.NANOSECONDS)
@State(Scope.Thread)
public class IterationBenchmark {

    @Param({"1", "2", "3", "4", "5", "6"})
    public int sizeOrder;

    private List<Integer> list;

    @Setup
    public void setup() {
        list = new ArrayList<Integer>();
        for (int c = 0; c < Math.pow(10, sizeOrder); c++) {
            list.add(10000 + c);
        }
    }

    @GenerateMicroBenchmark
    public void measureWrong() {
        for (Integer i : list) {}
    }

    @GenerateMicroBenchmark
    public void measureRight(BlackHole bh) {
        for (Integer i : list) {
            bh.consume(i);
        }
    }

}

Results

Linux, x86_64, JDK 7u40:

Benchmark                             (sizeOrder)   Mode   Samples         Mean   Mean error    Units
o.s.IterationBenchmark.measureRight             1   avgt        15       52.578        1.279    ns/op
o.s.IterationBenchmark.measureRight             2   avgt        15      500.127       27.728    ns/op
o.s.IterationBenchmark.measureRight             3   avgt        15     4762.948      247.602    ns/op
o.s.IterationBenchmark.measureRight             4   avgt        15    55926.913      542.441    ns/op
o.s.IterationBenchmark.measureRight             5   avgt        15   557258.750    22156.055    ns/op
o.s.IterationBenchmark.measureRight             6   avgt        15  5726578.719    54460.453    ns/op
o.s.IterationBenchmark.measureWrong             1   avgt        15       20.705        0.075    ns/op
o.s.IterationBenchmark.measureWrong             2   avgt        15      125.606        0.388    ns/op
o.s.IterationBenchmark.measureWrong             3   avgt        15     1162.701        8.058    ns/op
o.s.IterationBenchmark.measureWrong             4   avgt        15    11759.684       96.262    ns/op
o.s.IterationBenchmark.measureWrong             5   avgt        15   146168.024     3460.825    ns/op
o.s.IterationBenchmark.measureWrong             6   avgt        15  2201680.817    21412.890    ns/op

Is there code elimination or it is not so obvious?