GraphQL Federation Benchmark
An open benchmark of GraphQL federation routers/gateways. Each router is evaluated under the same conditions, on the same machine with the same subgraphs and the same GraphQL operation, so you can compare throughput, latency, memory and CPU on equal terms.
New results are published every day from a public workflow that anyone can inspect or rerun on their own hardware.
Latest run
- Run
- #402
- Completed
Results at a glance
Fusion is the fastest router in every scenario of run 402.
- Real-world
- 1,947 requests/s
- 4% faster than Hive Router
- Synthetic
- 2,653 requests/s
- 5.2% faster than Hive Router
- Burst traffic
- 2,733 requests/s
- 18.8% faster than Hive Router
Real-world results
GraphQL Federation specification
RouterMedian requests/sHTTP requests per second, as the median across the measured runs.
1,947, highest reported
All metrics for Fusion Nightly
- p95 latency95% of requests completed within this time.
- 30.9 ms
- p99.9 latency99.9% of requests completed within this time.
- 50.0 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 416 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 69.90%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.1%
1,929
All metrics for Fusion Nightly
- p95 latency95% of requests completed within this time.
- 31.5 ms
- p99.9 latency99.9% of requests completed within this time.
- 48.2 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 377 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 78.30%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.0%
1,893
All metrics for Fusion
- p95 latency95% of requests completed within this time.
- 31.9 ms
- p99.9 latency99.9% of requests completed within this time.
- 49.0 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 375 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 84.20%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.2%
1,175
All metrics for feddi
- p95 latency95% of requests completed within this time.
- 56.1 ms
- p99.9 latency99.9% of requests completed within this time.
- 76.5 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 1,186 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 95.80%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.2%
| Router/gateway | Median requests/sHTTP requests per second, as the median across the measured runs. | p95 latency95% of requests completed within this time. | p99.9 latency99.9% of requests completed within this time. | Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes. | Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads. | ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure. | Run varianceHow much throughput varied across the measured runs, as the coefficient of variation. |
|---|---|---|---|---|---|---|---|
1,947, highest reported | 30.9 ms | 50.0 ms | 416 MiB | 69.90 % | 100% | ±1.1% | |
1,929 | 31.5 ms | 48.2 ms | 377 MiB | 78.30 % | 100% | ±1.0% | |
1,893 | 31.9 ms | 49.0 ms | 375 MiB | 84.20 % | 100% | ±1.2% | |
1,175 | 56.1 ms | 76.5 ms | 1,186 MiB | 95.80 % | 100% | ±1.2% |
Apollo Federation v2
RouterMedian requests/sHTTP requests per second, as the median across the measured runs.
1,873, highest reported
All metrics for Hive Router
- p95 latency95% of requests completed within this time.
- 31.2 ms
- p99.9 latency99.9% of requests completed within this time.
- 47.2 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 132 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 68.30%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.2%
1,837
All metrics for Fusion Nightly
- p95 latency95% of requests completed within this time.
- 33.0 ms
- p99.9 latency99.9% of requests completed within this time.
- 51.8 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 374 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 79.50%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.0%
1,429
All metrics for Caliban
- p95 latency95% of requests completed within this time.
- 42.0 ms
- p99.9 latency99.9% of requests completed within this time.
- 59.0 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 5,397 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 98.30%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.5%
1,363
All metrics for Cosmo Router
- p95 latency95% of requests completed within this time.
- 45.4 ms
- p99.9 latency99.9% of requests completed within this time.
- 59.4 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 149 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 98.00%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.2%
1,282
All metrics for Grafbase Gateway
- p95 latency95% of requests completed within this time.
- 46.8 ms
- p99.9 latency99.9% of requests completed within this time.
- 62.2 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 101 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 73.40%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.2%
405
All metrics for Apollo Router
- p95 latency95% of requests completed within this time.
- 162 ms
- p99.9 latency99.9% of requests completed within this time.
- 210 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 184 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 100.00%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±2.5%
368
All metrics for Apollo Router
- p95 latency95% of requests completed within this time.
- 176 ms
- p99.9 latency99.9% of requests completed within this time.
- 224 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 199 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 100.00%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.9%
262
All metrics for Hive Gateway
- p95 latency95% of requests completed within this time.
- 234 ms
- p99.9 latency99.9% of requests completed within this time.
- 730 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 3,794 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 99.70%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±1.0%
256
All metrics for Apollo Gateway
- p95 latency95% of requests completed within this time.
- 288 ms
- p99.9 latency99.9% of requests completed within this time.
- 354 ms
- Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes.
- 2,142 MiB
- Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads.
- 99.10%
- ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure.
- 100%
- Run varianceHow much throughput varied across the measured runs, as the coefficient of variation.
- ±0.8%
| Router/gateway | Median requests/sHTTP requests per second, as the median across the measured runs. | p95 latency95% of requests completed within this time. | p99.9 latency99.9% of requests completed within this time. | Peak memoryThe highest sampled resident memory (RSS) of the router process and its child processes. | Average CPUAverage utilization of the router’s 4 hardware threads. 100% means both of its cores are fully busy on both threads. | ReliabilityThe share of requests that passed the checks for HTTP status, GraphQL errors and response structure. | Run varianceHow much throughput varied across the measured runs, as the coefficient of variation. |
|---|---|---|---|---|---|---|---|
1,873, highest reported | 31.2 ms | 47.2 ms | 132 MiB | 68.30 % | 100% | ±1.2% | |
1,837 | 33.0 ms | 51.8 ms | 374 MiB | 79.50 % | 100% | ±1.0% | |
1,429 | 42.0 ms | 59.0 ms | 5,397 MiB | 98.30 % | 100% | ±1.5% | |
1,363 | 45.4 ms | 59.4 ms | 149 MiB | 98.00 % | 100% | ±1.2% | |
1,282 | 46.8 ms | 62.2 ms | 101 MiB | 73.40 % | 100% | ±1.2% | |
405 | 162 ms | 210 ms | 184 MiB | 100.00 % | 100% | ±2.5% | |
368 | 176 ms | 224 ms | 199 MiB | 100.00 % | 100% | ±1.9% | |
262 | 234 ms | 730 ms | 3,794 MiB | 99.70 % | 100% | ±1.0% | |
256 | 288 ms | 354 ms | 2,142 MiB | 99.10 % | 100% | ±0.8% | |
Throughput over time
Median requests per second by date.
requests/s
22 Jul
GraphQL Federation specification
Apollo Federation v2
| Router | Run dates, versions and median requests per second |
|---|---|
| Apollo Gateway (Node 24) | 2026-07-22T11:52:09.000Z: 2.14.2, 268 requests/s, 2026-07-27T16:03:23.000Z: 2.14.3, 258 requests/s, 2026-07-30T16:01:56.000Z: 2.14.3, 265 requests/s, 2026-08-01T16:07:23.000Z: 2.14.3, 259 requests/s, 2026-08-05T16:56:21.000Z: 2.14.3, 264 requests/s, 2026-08-11T11:47:47.000Z: 2.14.3, 264 requests/s, 2026-08-20T16:40:29.000Z: 2.14.3, 257 requests/s, 2026-08-24T16:35:28.000Z: 2.14.3, 260 requests/s, 2026-08-27T17:26:23.000Z: 2.14.3, 268 requests/s, 2026-08-29T17:35:51.000Z: 2.14.3, 260 requests/s, 2026-08-31T16:39:02.000Z: 2.14.3, 265 requests/s, 2026-09-02T16:40:25.000Z: 2.14.3, 265 requests/s, 2026-09-09T16:36:14.000Z: 2.14.3, 261 requests/s, 2026-09-13T16:41:16.000Z: 2.14.3, 258 requests/s, 2026-09-17T16:37:09.000Z: 2.14.3, 259 requests/s, 2026-09-19T16:35:00.000Z: 2.14.3, 257 requests/s, 2026-09-22T16:40:03.000Z: 2.14.3, 260 requests/s, 2026-10-17T10:49:56.000Z: 2.14.4, 256 requests/s |
| Apollo Router 2.x (Rust) | 2026-07-22T11:52:09.000Z: 2.16.0, 424 requests/s, 2026-07-27T16:03:23.000Z: 2.16.1, 394 requests/s, 2026-07-30T16:01:56.000Z: 2.16.1, 433 requests/s, 2026-08-01T16:07:23.000Z: 2.16.1, 399 requests/s, 2026-08-05T16:56:21.000Z: 2.16.1, 429 requests/s, 2026-08-11T11:47:47.000Z: 2.16.1, 435 requests/s, 2026-08-20T16:40:29.000Z: 2.16.1, 408 requests/s, 2026-08-24T16:35:28.000Z: 2.16.1, 431 requests/s, 2026-08-27T17:26:23.000Z: 2.16.1, 395 requests/s, 2026-08-29T17:35:51.000Z: 2.16.1, 433 requests/s, 2026-08-31T16:39:02.000Z: 2.16.1, 399 requests/s, 2026-09-02T16:40:25.000Z: 2.16.1, 397 requests/s, 2026-09-09T16:36:14.000Z: 2.16.1, 426 requests/s, 2026-09-13T16:41:16.000Z: 2.16.1, 399 requests/s, 2026-09-17T16:37:09.000Z: 2.16.1, 390 requests/s, 2026-09-19T16:35:00.000Z: 2.16.1, 431 requests/s, 2026-09-22T16:40:03.000Z: 2.16.1, 433 requests/s, 2026-10-17T10:49:56.000Z: 2.18.0, 405 requests/s |
| Apollo Router 3.x (Rust) | 2026-10-16T10:24:10.000Z: 3.0.0-preview.0, 402 requests/s, 2026-10-17T10:49:56.000Z: 3.0.0-preview.0, 368 requests/s |
| Caliban (JVM 25) | 2026-10-16T10:24:10.000Z: 3.2.0, 1,277 requests/s, 2026-10-17T10:49:56.000Z: 3.2.0, 1,429 requests/s |
| Cosmo Router (Go) | 2026-07-22T11:52:09.000Z: 0.331.1, 1,166 requests/s, 2026-07-27T16:03:23.000Z: 0.334.0, 1,164 requests/s, 2026-07-30T16:01:56.000Z: 0.334.0, 1,230 requests/s, 2026-08-01T16:07:23.000Z: 0.334.0, 1,189 requests/s, 2026-08-05T16:56:21.000Z: 0.334.0, 1,229 requests/s, 2026-08-11T11:47:47.000Z: 0.334.0, 1,222 requests/s, 2026-08-20T16:40:29.000Z: 0.334.0, 1,174 requests/s, 2026-08-24T16:35:28.000Z: 0.334.0, 1,229 requests/s, 2026-08-27T17:26:23.000Z: 0.334.0, 1,214 requests/s, 2026-08-29T17:35:51.000Z: 0.334.0, 1,230 requests/s, 2026-08-31T16:39:02.000Z: 0.334.0, 1,216 requests/s, 2026-09-02T16:40:25.000Z: 0.334.0, 1,153 requests/s, 2026-09-09T16:36:14.000Z: 0.334.0, 1,214 requests/s, 2026-09-13T16:41:16.000Z: 0.334.0, 1,178 requests/s, 2026-09-17T16:37:09.000Z: 0.334.0, 1,231 requests/s, 2026-09-19T16:35:00.000Z: 0.334.0, 1,229 requests/s, 2026-09-22T16:40:03.000Z: 0.334.0, 1,221 requests/s, 2026-10-17T10:49:56.000Z: 0.359.0, 1,363 requests/s |
| Grafbase Gateway (Rust) | 2026-07-22T11:52:09.000Z: 0.53.5, 1,324 requests/s, 2026-07-27T16:03:23.000Z: 0.53.5, 1,284 requests/s, 2026-07-30T16:01:56.000Z: 0.53.5, 1,288 requests/s, 2026-08-01T16:07:23.000Z: 0.53.5, 1,290 requests/s, 2026-08-05T16:56:21.000Z: 0.53.5, 1,276 requests/s, 2026-08-11T11:47:47.000Z: 0.53.5, 1,269 requests/s, 2026-08-20T16:40:29.000Z: 0.53.5, 1,308 requests/s, 2026-08-24T16:35:28.000Z: 0.53.5, 1,308 requests/s, 2026-08-27T17:26:23.000Z: 0.53.5, 1,320 requests/s, 2026-08-29T17:35:51.000Z: 0.53.5, 1,316 requests/s, 2026-08-31T16:39:02.000Z: 0.53.5, 1,276 requests/s, 2026-09-02T16:40:25.000Z: 0.53.5, 1,306 requests/s, 2026-09-09T16:36:14.000Z: 0.53.5, 1,285 requests/s, 2026-09-13T16:41:16.000Z: 0.53.5, 1,313 requests/s, 2026-09-17T16:37:09.000Z: 0.53.5, 1,317 requests/s, 2026-09-19T16:35:00.000Z: 0.53.5, 1,314 requests/s, 2026-09-22T16:40:03.000Z: 0.53.5, 1,305 requests/s, 2026-10-17T10:49:56.000Z: 0.53.5, 1,282 requests/s |
| Hive Gateway (Node 24) | 2026-07-22T11:52:09.000Z: 2.10.4, 258 requests/s, 2026-07-27T16:03:23.000Z: 2.10.8, 258 requests/s, 2026-07-30T16:01:56.000Z: 2.10.8, 254 requests/s, 2026-08-01T16:07:23.000Z: 2.10.8, 264 requests/s, 2026-08-05T16:56:21.000Z: 2.10.8, 264 requests/s, 2026-08-11T11:47:47.000Z: 2.10.8, 253 requests/s, 2026-08-20T16:40:29.000Z: 2.10.8, 265 requests/s, 2026-08-24T16:35:28.000Z: 2.10.8, 258 requests/s, 2026-08-27T17:26:23.000Z: 2.10.8, 261 requests/s, 2026-08-29T17:35:51.000Z: 2.10.8, 258 requests/s, 2026-08-31T16:39:02.000Z: 2.10.8, 263 requests/s, 2026-09-02T16:40:25.000Z: 2.10.8, 263 requests/s, 2026-09-09T16:36:14.000Z: 2.10.8, 262 requests/s, 2026-09-13T16:41:16.000Z: 2.10.8, 253 requests/s, 2026-09-17T16:37:09.000Z: 2.10.8, 263 requests/s, 2026-09-19T16:35:00.000Z: 2.10.8, 256 requests/s, 2026-09-22T16:40:03.000Z: 2.10.8, 262 requests/s, 2026-10-17T10:49:56.000Z: 2.15.2, 262 requests/s |
| Hive Gateway · Router Runtime (Node) | 2026-07-22T11:52:09.000Z: 2.10.4, 550 requests/s, 2026-07-27T16:03:23.000Z: 2.10.8, 554 requests/s, 2026-07-30T16:01:56.000Z: 2.10.8, 558 requests/s, 2026-08-01T16:07:23.000Z: 2.10.8, 562 requests/s, 2026-08-05T16:56:21.000Z: 2.10.8, 552 requests/s, 2026-08-11T11:47:47.000Z: 2.10.8, 563 requests/s, 2026-08-20T16:40:29.000Z: 2.10.8, 557 requests/s, 2026-08-24T16:35:28.000Z: 2.10.8, 560 requests/s, 2026-08-27T17:26:23.000Z: 2.10.8, 559 requests/s, 2026-08-28T19:36:23.000Z: 2.10.8, 561 requests/s, 2026-08-30T16:37:14.000Z: 2.10.8, 568 requests/s, 2026-09-01T16:39:14.000Z: 2.10.8, 568 requests/s, 2026-09-03T16:39:54.000Z: 2.10.8, 549 requests/s, 2026-09-12T16:35:25.000Z: 2.10.8, 544 requests/s, 2026-09-16T16:36:50.000Z: 2.10.8, 556 requests/s, 2026-09-18T16:36:32.000Z: 2.10.8, 568 requests/s, 2026-09-20T16:36:16.000Z: 2.10.8, 575 requests/s, 2026-10-16T10:24:10.000Z: 2.15.2, 498 requests/s |
| Hive Router (Rust) | 2026-07-22T11:52:09.000Z: 0.0.83, 1,864 requests/s, 2026-07-27T16:03:23.000Z: 0.0.84, 1,835 requests/s, 2026-07-30T16:01:56.000Z: 0.0.84, 1,858 requests/s, 2026-08-01T16:07:23.000Z: 0.0.84, 1,848 requests/s, 2026-08-05T16:56:21.000Z: 0.0.84, 1,808 requests/s, 2026-08-11T11:47:47.000Z: 0.0.84, 1,833 requests/s, 2026-08-20T16:40:29.000Z: 0.0.84, 1,860 requests/s, 2026-08-24T16:35:28.000Z: 0.0.84, 1,854 requests/s, 2026-08-27T17:26:23.000Z: 0.0.84, 1,822 requests/s, 2026-08-29T17:35:51.000Z: 0.0.84, 1,865 requests/s, 2026-08-31T16:39:02.000Z: 0.0.84, 1,823 requests/s, 2026-09-02T16:40:25.000Z: 0.0.84, 1,857 requests/s, 2026-09-09T16:36:14.000Z: 0.0.84, 1,818 requests/s, 2026-09-13T16:41:16.000Z: 0.0.84, 1,819 requests/s, 2026-09-17T16:37:09.000Z: 0.0.84, 1,853 requests/s, 2026-09-19T16:35:00.000Z: 0.0.84, 1,836 requests/s, 2026-09-22T16:40:03.000Z: 0.0.84, 1,809 requests/s, 2026-10-17T10:49:56.000Z: 0.3.5, 1,873 requests/s |
| Fusion (.NET 10) | 2026-07-22T11:52:09.000Z: 16.5.1, 1,859 requests/s, 2026-07-27T16:03:23.000Z: 16.5.1, 1,875 requests/s, 2026-07-30T16:01:56.000Z: 16.5.1, 1,862 requests/s, 2026-08-01T16:07:23.000Z: 16.5.1, 1,864 requests/s, 2026-08-05T16:56:21.000Z: 16.5.1, 1,862 requests/s, 2026-08-11T11:47:47.000Z: 16.6.0, 1,888 requests/s, 2026-08-20T16:40:29.000Z: 16.6.1, 1,899 requests/s, 2026-08-24T16:35:28.000Z: 16.6.1, 1,893 requests/s, 2026-08-27T17:26:23.000Z: 16.6.1, 1,873 requests/s, 2026-08-29T17:35:51.000Z: 16.6.2, 1,893 requests/s, 2026-08-31T16:39:02.000Z: 16.6.2, 1,898 requests/s, 2026-09-02T16:40:25.000Z: 16.6.2, 1,885 requests/s, 2026-09-09T16:36:14.000Z: 16.6.4, 1,875 requests/s, 2026-09-13T16:41:16.000Z: 16.6.6, 1,878 requests/s, 2026-09-17T16:37:09.000Z: 16.6.6, 1,880 requests/s, 2026-09-19T16:35:00.000Z: 16.6.6, 1,893 requests/s, 2026-09-22T16:40:03.000Z: 16.6.6, 1,875 requests/s, 2026-10-17T10:49:56.000Z: 16.6.8, 1,893 requests/s |
| Fusion Nightly (.NET 10) | 2026-07-26T16:01:42.000Z: 16.6.0-p.3, 1,866 requests/s, 2026-07-29T16:13:06.000Z: 16.6.0-p.6, 1,877 requests/s, 2026-07-31T16:10:01.000Z: 16.6.0-p.8, 1,887 requests/s, 2026-08-03T16:01:43.000Z: 16.6.0-p.13, 1,881 requests/s, 2026-08-14T16:49:42.000Z: 16.6.1-p.2, 1,881 requests/s, 2026-08-23T16:36:55.000Z: 16.6.2-p.6, 1,891 requests/s, 2026-08-25T16:40:02.000Z: 16.6.2-p.7, 1,900 requests/s, 2026-08-28T19:36:23.000Z: 16.6.2-p.8, 1,887 requests/s, 2026-08-30T16:37:14.000Z: 16.7.0-p.1, 1,894 requests/s, 2026-08-31T16:39:02.000Z: 16.7.0-p.1, 1,889 requests/s, 2026-09-02T16:40:25.000Z: 16.7.0-p.2, 1,877 requests/s, 2026-09-09T16:36:14.000Z: 16.7.0-p.5, 1,873 requests/s, 2026-09-13T16:41:16.000Z: 16.7.0-p.6, 1,883 requests/s, 2026-09-17T16:37:09.000Z: 16.7.0-p.7, 1,882 requests/s, 2026-09-19T16:35:00.000Z: 16.7.0-p.8, 1,881 requests/s, 2026-09-22T16:40:03.000Z: 16.7.0-p.9, 1,891 requests/s, 2026-10-17T10:49:56.000Z: 16.7.0-p.28, 1,929 requests/s |
| Fusion Nightly (.NET 11) | 2026-07-26T16:01:42.000Z: 16.6.0-p.3, 1,870 requests/s, 2026-07-29T16:13:06.000Z: 16.6.0-p.6, 1,852 requests/s, 2026-07-31T16:10:01.000Z: 16.6.0-p.8, 1,869 requests/s, 2026-08-03T16:01:43.000Z: 16.6.0-p.13, 1,872 requests/s, 2026-08-14T16:49:42.000Z: 16.6.1-p.2, 1,881 requests/s, 2026-08-23T16:36:55.000Z: 16.6.2-p.6, 1,878 requests/s, 2026-08-25T16:40:02.000Z: 16.6.2-p.7, 1,873 requests/s, 2026-08-28T19:36:23.000Z: 16.6.2-p.8, 1,883 requests/s, 2026-08-30T16:37:14.000Z: 16.7.0-p.1, 1,897 requests/s, 2026-08-31T16:39:02.000Z: 16.7.0-p.1, 1,872 requests/s, 2026-09-02T16:40:25.000Z: 16.7.0-p.2, 1,852 requests/s, 2026-09-09T16:36:14.000Z: 16.7.0-p.5, 1,892 requests/s, 2026-09-13T16:41:16.000Z: 16.7.0-p.6, 1,879 requests/s, 2026-09-17T16:37:09.000Z: 16.7.0-p.7, 1,878 requests/s, 2026-09-19T16:35:00.000Z: 16.7.0-p.8, 1,887 requests/s, 2026-09-22T16:40:03.000Z: 16.7.0-p.9, 1,894 requests/s, 2026-10-17T10:49:56.000Z: 16.7.0-p.28, 1,947 requests/s |
| Fusion Nightly (.NET 10) | 2026-07-26T16:01:42.000Z: 16.6.0-p.3, 1,753 requests/s, 2026-07-29T16:13:06.000Z: 16.6.0-p.6, 1,756 requests/s, 2026-07-31T16:10:01.000Z: 16.6.0-p.8, 1,760 requests/s, 2026-08-03T16:01:43.000Z: 16.6.0-p.13, 1,760 requests/s, 2026-08-14T16:49:42.000Z: 16.6.1-p.2, 1,798 requests/s, 2026-08-23T16:36:55.000Z: 16.6.2-p.6, 1,790 requests/s, 2026-08-25T16:40:02.000Z: 16.6.2-p.7, 1,806 requests/s, 2026-08-28T19:36:23.000Z: 16.6.2-p.8, 1,812 requests/s, 2026-08-30T16:37:14.000Z: 16.7.0-p.1, 1,798 requests/s, 2026-08-31T16:39:02.000Z: 16.7.0-p.1, 1,794 requests/s, 2026-09-02T16:40:25.000Z: 16.7.0-p.2, 1,796 requests/s, 2026-09-09T16:36:14.000Z: 16.7.0-p.5, 1,818 requests/s, 2026-09-13T16:41:16.000Z: 16.7.0-p.6, 1,790 requests/s, 2026-09-17T16:37:09.000Z: 16.7.0-p.7, 1,808 requests/s, 2026-09-19T16:35:00.000Z: 16.7.0-p.8, 1,798 requests/s, 2026-09-22T16:40:03.000Z: 16.7.0-p.9, 1,802 requests/s, 2026-10-17T10:49:56.000Z: 16.7.0-p.28, 1,837 requests/s |
| feddi (JVM 25) | 2026-10-16T10:24:10.000Z: e91d605ed222, 1,120 requests/s, 2026-10-17T10:49:56.000Z: e91d605ed222, 1,175 requests/s |
Test conditions
Procedure
Every scenario runs these steps in order, one router at a time.
Start
The router runs on 2 dedicated physical cores (4 hardware threads). CPU boost is disabled to reduce clock-speed variation.
Warm up
One run of the full scenario length primes the router before anything is measured. Its results are discarded.
Measure
9 more runs of the same length follow. Each one sends the same GraphQL operation with the load profile of the scenario.
Check responses
A request only counts as a success when it returns HTTP 200 without GraphQL errors.
Report the median
Results use the median requests per second of the 9 runs, and run variance shows how much the runs differed.
Hardware
- Processor
- AMD Ryzen 7 5700G with Radeon Graphics
- CPU topology
- 8 physical cores (16 hardware threads, SMT).
- Memory
- 122 GB
Software
- Operating system
- Linux 6.8.0-147-generic
- Subgraphs
- Hot Chocolate 16.6.8 (.NET 10.0.13)
CPU pinning
- Hardware thread 0, physical core 0: OS & monitoring
- Hardware thread 8, physical core 0: OS & monitoring
- Hardware thread 1, physical core 1: Load generator
- Hardware thread 9, physical core 1: Load generator
- Hardware thread 2, physical core 2: Router
- Hardware thread 10, physical core 2: Router
- Hardware thread 3, physical core 3: Router
- Hardware thread 11, physical core 3: Router
- Hardware thread 4, physical core 4: Subgraphs
- Hardware thread 12, physical core 4: Subgraphs
- Hardware thread 5, physical core 5: Subgraphs
- Hardware thread 13, physical core 5: Subgraphs
- Hardware thread 6, physical core 6: Subgraphs
- Hardware thread 14, physical core 6: Subgraphs
- Hardware thread 7, physical core 7: Subgraphs
- Hardware thread 15, physical core 7: Subgraphs
- OS & monitoring
- Load generator
- Router
- Subgraphs
Processes are pinned with taskset; all other processes are moved onto core 0. Kernel threads and interrupts can still run on any core.
Published by ChilliCream, the team behind Fusion, using a harness based on The Guild's gateway benchmarks.