Benchmark Report
Tick spikes · Network (NBT)
The worst ticks are several times the mean. Average TPS stays fine while players feel the stutter.
- mspt_avg = 19 ms
- mspt_p99 = 58.63 ms
- spike_ratio = 3.09 ratio
- sample_count = 98 count
- spike_ticks = 2 count
- spike_window_ticks = 420 count
- spike_threshold_ms = 50 ms
- spike_ticks_with_gc = 1 count
- spike_ticks_with_throttle = 0 count
- spike_ticks_with_steal = 0 count
- spike_tick_ms = 355.6 ms
- spike_gc_pause_ms = 106 ms
- spike_throttled_ms = 0 ms
- spike_sample_interval_ms = 40 ms
- explained_share_threshold = 0.5 ratio
- explained_time_share_threshold = 0.25 ratio
Weakest test: Mob AI, 9.25 TPS on average. The 15 other tests hold at least 19.94 TPS.
Compared with other servers
Every measured server counts here, including private, anonymous and expired reports. Each server counts once, with its best run.
This report scores better than
88%
of the 9 servers running Paper & forks
Total score 121,232 · group median 85,678
Top quarter- Single Core
Better than 79% · 162,013 vs median 104,683 · Top quarter
- Gameplay
Better than 74% · 69,627 vs median 62,624
- Exploration
Better than 88% · 93,680 vs median 81,949 · Top quarter
- Entities
Better than 69% · 79,161 vs median 68,912
- Mechanics
Better than 88% · 46,941 vs median 46,275 · Top quarter
- Hardware
Better than 88% · 57,706 vs median 36,859 · Top quarter
- Memory
Better than 88% · 33,940 vs median 25,490 · Top quarter
- Disk
Better than 82% · 57,686 vs median 52,420 · Top quarter
- Multi-Core
Better than 83% · 105,543 vs median 67,413 · Top quarter
Test by test
Each tick test's average MSPT (lower is better) and TPS, against the same group, each server with the same run as above. A test shows when at least 5 servers of the group passed it. The bar follows the MSPT.
- Block Physics
Better than 88% · MSPT 8.3 ms vs median 17 ms · TPS 20 vs median 20 · Top quarter
- Bone Meal Growth
Better than 88% · MSPT 1.2 ms vs median 2 ms · TPS 20 vs median 20 · Top quarter
- Chunk Loading
Better than 88% · MSPT 2.8 ms vs median 4.3 ms · TPS 20 vs median 19.7 · Top quarter
- Chunk Ticking
Better than 88% · MSPT 11.8 ms vs median 18 ms · TPS 20 vs median 20 · Top quarter
- Explosion
Better than 88% · MSPT 2.8 ms vs median 5.2 ms · TPS 19.9 vs median 20 · Top quarter
- Hopper
Better than 75% · MSPT 1.6 ms vs median 2.4 ms · TPS 20 vs median 19.9 · Top quarter
- Lighting Update
Better than 78% · MSPT 1.9 ms vs median 2.4 ms · TPS 20 vs median 20 · Top quarter
- Mob AI
Better than 70% · MSPT 127.4 ms vs median 180.4 ms · TPS 9.3 vs median 6.8
- Redstone
Better than 56% · MSPT 20.9 ms vs median 24.7 ms · TPS 20 vs median 18.5
- Ticking Tile Entities
Better than 88% · MSPT 1.6 ms vs median 3.4 ms · TPS 20 vs median 20 · Top quarter
- World Save
Better than 88% · MSPT 1 ms vs median 1.8 ms · TPS 20 vs median 20 · Top quarter
Scored with version 8.3.0 of the scoring rules. Groups of fewer than 5 servers are never used. Updated Oct 27, 2026, 6:40 PM UTC. Community trends · All measurements by CPU
What matters
Read from the measurements, never estimatedNon-default server configuration
Compare with care against a server running default settings.
- spawn-limit.monster 50 (default 70)
- spigot:entity-activation-range.monsters 24 (default 32)
- spigot:max-tnt-per-tick 1200 (default 100)
Tick spikes
The worst ticks are several times the mean. Average TPS stays fine while players feel the stutter.
- mspt_avg = 19 ms
- mspt_p99 = 58.63 ms
- spike_ratio = 3.09 ratio
- sample_count = 98 count
- spike_ticks = 2 count
- spike_window_ticks = 420 count
- spike_threshold_ms = 50 ms
- spike_ticks_with_gc = 1 count
- spike_ticks_with_throttle = 0 count
- spike_ticks_with_steal = 0 count
- spike_tick_ms = 355.6 ms
- spike_gc_pause_ms = 106 ms
- spike_throttled_ms = 0 ms
- spike_sample_interval_ms = 40 ms
- explained_share_threshold = 0.5 ratio
- explained_time_share_threshold = 0.25 ratio
›+1 more finding
The run started on a JVM that had just started, or that had not run a bench since it started: code was still being compiled and the heap still growing. The first run after a restart can differ from the next ones.
- jvm_uptime_s = 9 s
- bench_runs_since_start = 0 count
- threshold_s = 300 s
A finding stays silent rather than attribute a cause without evidence. An absent cause is an answer, not an omission.
Test by test
Problems first — select a row for the full test- Mob AIEntities9.25UnstableUnstable
- ExplosionMechanics19.94StableUnstable
- Network (NBT)Network19.95ModerateUnstable
- Multi-Core CPUCPU19.99StableHealthy
- Block PhysicsSingle-Core Stress20.00StableHealthy
- Bone Meal GrowthMechanics20.00StableHealthy
- Chunk LoadingExploration20.00ModerateHealthy
- Chunk TickingExploration20.00StableHealthy
- Disk PerformanceMemory & Storage20.00StableHealthy
- HopperMechanics20.00StableHealthy
- Lighting UpdateExploration20.00ModerateHealthy
- Memory PerformanceMemory & Storage20.00StableHealthy
- RedstoneSingle-Core Stress20.00effective 20.0UnstableHealthy
- Single-Core (tick-aligned)CPU20.00StableHealthy
- Ticking Tile EntitiesMechanics20.00StableHealthy
- World SaveMechanics20.00StableHealthy
Settings your measurements justify
Each setting below is triggered by a measurement from this report, and names the test to replay to find out whether it helped.
Shrink the monster activation range
world-settings.default.entity-activation-range.monsters: 24Measured : mobAI.mspt.avg 127.4 ms (threshold 35.0 ms)
Mob AI costs more per tick than the budget allows. The activation range decides how far from a player a monster keeps thinking; shrinking it puts distant ones to sleep without removing them.
Test to replay : mobAI
These settings trade a little gameplay fidelity for tick budget. Apply one at a time and replay the named test: the effect stays a hypothesis until you have measured it.
Briefing for a language model
Paste this into the assistant of your choice to have it rewritten in prose. It already carries every number, so the model has none left to invent.
{
"format": "voxelbench.tuning.v1",
"instruction": "Rewrite each recommendation below as plain prose for a server operator. Every number you are allowed to use is already in this document: the measured value, its threshold, and the proposed setting. Do not compute, estimate or predict any other number, and never state an expected gain. Keep every setting name and value exactly as written.",
"server": {
"type": "paper",
"minecraft": "26.3",
"java": "25.0.4.1"
},
"recommendations": [
{
"id": "spigot.portee-activation-monstres",
"family": "spigot",
"measure": "mobAI.mspt.avg",
"value": 127.4,
"unit": "ms",
"threshold": 35,
"control_test": "mobAI",
"file": "spigot.yml",
"setting": "world-settings.default.entity-activation-range.monsters",
"proposed_value": "24",
"current_value": null
}
]
}Java start-up line
The options this server was started with, checked against its Java version. Corrections fix what is certainly wrong; leads to test are settings to measure, never applied for you.
Current line (3 arguments)
Values of system properties, agents and file paths are never shown: they appear as <redacted>.
-Xms24276M -Xmx24276M -XX:MaxRAMPercentage=95.0
To correct
- DangerHeap too close to the machine's memory
-Xmx24276MThe heap may use 24276 MiB of the machine's 25804 MiB, which leaves 1528 MiB for everything else (code, threads, network buffers, the system). Under load the server can be killed without any Java error. The corrected line keeps 3871 MiB outside the heap.
Corrected line to copy
- Changed
-Xmx24276M-Xmx21933Mleaves 3871 MiB outside the heap. - Changed
-Xms24276M-Xms21933Mthe initial heap cannot exceed the maximum.
java -Xms21933M -Xmx21933M -XX:MaxRAMPercentage=95.0 -jar server.jar noguiReplace server.jar with your server's jar. Paste the line where your server is started: the start-up parameters (or JVM arguments) of your hosting panel, or your start.sh / start.bat. Only the corrections above differ from your current line.
To test
Performance settings to try one at a time, then measure with a benchmark before and after. None of them is applied in the corrected line, and none comes with a promised gain.
Settings documented by PaperMC for Minecraft servers: they size G1's young generation for the game's very high allocation rate and start collections earlier. Initial and maximum heap at the same size, with AlwaysPreTouch, commit the whole heap at start-up: proposed only because that heap already stays under the memory limit.
-XX:+UseG1GC -XX:+ParallelRefProcEnabled -XX:MaxGCPauseMillis=200 -XX:+UnlockExperimentalVMOptions -XX:+DisableExplicitGC -XX:+AlwaysPreTouch -XX:G1NewSizePercent=30 -XX:G1MaxNewSizePercent=40 -XX:G1HeapRegionSize=8M -XX:G1ReservePercent=20 -XX:G1HeapWastePercent=5 -XX:G1MixedGCCountTarget=4 -XX:InitiatingHeapOccupancyPercent=15 -XX:G1MixedGCLiveThresholdPercent=90 -XX:G1RSetUpdatingPauseTimePercent=5 -XX:SurvivorRatio=32 -XX:+PerfDisableSharedMem -XX:MaxTenuringThreshold=1No measurement of this run points to it: it stays a lead to measure.
sourceA collector with very short pauses for large heaps, at the cost of more CPU and memory. It replaces the current collector: remove the current collector option and its own tuning options, then measure. From Java 23 the generational mode is the default.
-XX:+UseZGCNo measurement of this run points to it: it stays a lead to measure.
sourceRe-run and compare
- Apply the corrected line where your server starts (panel start-up parameters, start.sh).
- Restart the server.
- Run a new benchmark:
/bench start - Compare the new report with this one.
This report is the before; add the new report to the comparison once it is in. A single run on each side says little: the gap between two runs of an unchanged server is noise.
Run conditions
What the plugin saw of the host during the benchmark, and what the site concludes from it. The plugin reports facts; the verdicts and their thresholds are the site's, the same ones the diagnosis and the API use.
The reference computation timed during the run kept its pace, and the hypervisor took no significant CPU time.
A CPU quota, a reduced CPU set or a memory limit applies to the server.
Contention during the run
- Reference computation slowdown
- 0.6 % (threshold 15 %)3 timings: 12.5 ms · 12.6 ms · 12.5 ms (a slow first timing alone does not count) — judged on the median of at least 40 samples per timing (plugin 2.6.2); host noise 4.1 %, the threshold widens to it, from 15 to 30 % — wait for the server to settle before Hopper, after chunk loading: 0.0 s (limit 30.0 s, after chunk generation)
- CPU time stolen by the hypervisor
- 0 % (threshold 5 %)
- Scheduling periods ended throttled by the quota
- 0 % (threshold 25 %)0 ms
- Time a task waited for a core
- 0.1 % (threshold 40 %)
Limits seen by the server
- CPU quota
- 12 cores
- CPU set
- 0-11 (12 cores)
- Memory limit
- 25.2 GiB
- Host logical CPUs
- 12
- Host memory
- 25.4 GiB
- Container signals
- dockerenv, cgroup-v2-namespace, overlay-root, pterodactyl-env
Storage
- Filesystem
- xfs · Local filesystem
- Direct 4K reads
- Honoured (69.6 µs against 0.3 µs from cache)
Single-core measurement
- Throughput (wall clock)
- 651.9M ops/s651.7M ops/s over the thread's CPU time
- Thread CPU time / wall time
- 1.000 (threshold 0.900)Below 1, the thread was not running for part of its slices (quota, neighbours, hypervisor steal when counted, JVM pauses). Close to 1 proves nothing.
- Spread from second to second
- 3.1 % (threshold 40 %)p10 642.3M · p50 659.4M · p90 662.5M ops/s over 9 seconds
- GC pauses during the measurement
- 0 ms (threshold 50 ms)0 collections, 0 ms of collection time
- Highest current CPU frequency
- not exposed by this systemadvertised maximum: 3,187 MHz
Witnesses of the single-core test (plugin 2.5.0). The score does not read this test, and none of these figures changes the run's stability verdict.
Host, memory and server state
- Time a task waited for storage
- 5.6 % (all tasks at once: 5.6 %)includes the disk test, which waits for storage by design: not judged for the run
- Time a task stalled on memory
- 0 % (all tasks at once: 0 %) (threshold 5 %)
- CPU quota during the run
- 12 coresno change observed
- Container memory
- peak 18,302 MiBlimit events: high 0 · max 0 · OOM kills 0
- Runnable tasks on the machine
- up to 11.3 on average during a test, for 12 logical CPUs
- Host uptime at the start
- 55 h
- Server at the start of the run
- JVM up for 0.2 minfirst bench since the JVM startedoutside the bench world: 0 players · 130 chunks · 68 entities
Run pressures from plugin 2.4.0, the rest from plugin 2.6.0. None of these figures changes the score or the run's stability verdict; the diagnosis names the tests they concern.
Thresholds and their reasons are published in the benchmark methodology. Rules rc-7.
Every measurement
Each test in full. Tests in trouble are open; the others fold to their summary line.
Single-Core Stress
RedstoneHealthy20.00 TPS20.9 ms34.9s
Single-core stress via intensive redstone circuit updates.
- Heavy garbage collection7 collections, 368ms total
Percentiles and stability
Raw data (68 fields)
Block PhysicsHealthy20.00 TPS8.3 ms24.9s
Single-core stress via falling-block physics.
- Heavy garbage collection2 collections, 262ms total
Percentiles and stability
Raw data (71 fields)
Exploration
Chunk LoadingHealthy20.00 TPS2.8 ms7.6s
Chunk generation and loading speed across dispersed zones.
- Heavy garbage collection4 collections, 1256ms total
Percentiles and stability
Raw data (61 fields)
Chunk TickingHealthy20.00 TPS11.8 ms40.9s
Server performance when ticking many loaded chunks with random tick updates.
- Heavy garbage collection2 collections, 318ms total
Percentiles and stability
Raw data (63 fields)
Lighting UpdateHealthy20.00 TPS1.9 ms24.6s
Lighting recomputation throughput on block place / break.
- Heavy garbage collection2 collections, 298ms total
Percentiles and stability
Raw data (58 fields)
Entities
Mob AIUnstable9.25 TPS127.4 ms30.3s
Complex mob AI behaviours (villagers, iron golems, hostile mobs).
- Heavy garbage collection3 collections, 456ms total
- The run did not hold steadyTPS avg=9.25<19, TPS P1=5.00<15, TPS StdDev=2.57>2, TPS min=5.00 (54% of avg)
Percentiles and stability
Raw data (80 fields)
Mechanics
HopperHealthy20.00 TPS1.6 ms19.2s
Intensive hopper chain item transfers.
- Heavy garbage collection2 collections, 281ms total
Percentiles and stability
Raw data (70 fields)
ExplosionUnstable19.94 TPS2.8 ms17.0s
Massive TNT explosions and block destruction.
- Heavy garbage collection3 collections, 357ms total
- The run did not hold steadyTPS P1=15.00<15
Percentiles and stability
Raw data (112 fields)
Ticking Tile EntitiesHealthy20.00 TPS1.6 ms36.0s
Many ticking tile entities (furnaces, hoppers, etc.).
- Heavy garbage collection2 collections, 291ms total
Percentiles and stability
Raw data (60 fields)
World SaveHealthy20.00 TPS1.0 ms4.8s
World save speed and TPS impact during save operations.
- Heavy garbage collection3 collections, 320ms total
Percentiles and stability
Raw data (58 fields)
Bone Meal GrowthHealthy20.00 TPS1.2 ms23.3s
Rapid crop and tree growth via bone meal.
- Heavy garbage collection1 collections, 136ms total
Percentiles and stability
Raw data (62 fields)
CPU
Single-Core (tick-aligned)Healthy20.00 TPS3.1 ms10.0s
Single-thread compute throughput measured on the main thread under the tick scheduler.
- Heavy garbage collection3 collections, 330ms total
Percentiles and stability
Raw data (63 fields)
Multi-Core CPUHealthy19.99 TPS1.1 ms7.9s
Parallel computation throughput across worker threads.
- Heavy garbage collection1 collections, 105ms total
Percentiles and stability
Raw data (58 fields)
Memory & Storage
Memory PerformanceHealthy20.00 TPS1.5 ms18.7s
RAM bandwidth and latency.
JVM measurements — do not reflect actual bare-metal performance.
- Heavy garbage collection4 collections, 414ms total
Percentiles and stability
Raw data (63 fields)
Disk PerformanceHealthy20.00 TPS1.3 ms51.0s
Sequential and random 4K read/write performance.
JVM measurements — do not reflect actual bare-metal performance.
- Heavy garbage collection1 collections, 132ms total
Percentiles and stability
Raw data (57 fields)
Network
Network (NBT)Unstable19.95 TPS19.0 ms20.0s
Serialisation throughput — proxy for the rate at which the server can ship world data to clients.
- Heavy garbage collection3 collections, 112ms total
- The run did not hold steadyTPS P1=15.00<15
Percentiles and stability
Raw data (57 fields)
›Machine and serverIntel(R) Core(TM) i9-14900K · Paper · 26.3
Score Breakdown
Detailed sub-category scores