--- title: The school on the CPU and on the GPU — Mova description: Mova's school run on the CPU (exact) and in the GPU-enhanced mode: 75.1% of the tests answered the same, +193 tests right on the GPU, course by course with the time of each. --- Elamur: **Mova** · [Parse](https://mova.elamur.ai/free/en/parse/) · [Dictionary](https://md.dictionary.elamur.ai/free/en/) · [Translate](https://md.translate.elamur.ai/free/en/) · [Research](https://md.research.elamur.ai/free/en/) · [MCP](https://mcp.elamur.ai/) · [Groupants](https://md.groupants.elamur.ai/free/en/) [Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/school-run/gpu/) [home](https://md.mova.elamur.ai/free/en/) / [at school](https://md.mova.elamur.ai/free/en/school-run/) / CPU and GPU # The school on the CPU and on the GPU Mova runs in two modes. **CPU only** is the reference: exact, and what [the school run](https://md.mova.elamur.ai/free/en/school-run/) shows. **GPU enhanced** (`MOVA_EXEC=gpu`) reads the lessons and the tests with the GPU parser instead of the CPU one, an approximant; the student itself, its memory and its choices, is the same code. Here both modes take the same courses, test by test. - **75.1%** — the same choice — 37275 of 49635 tests - **+193** — tests right on the GPU — 18882 against 18689 on the CPU (38.04% against 37.65%) - **18 / 6** — courses gained / lost — on the GPU - **1.32× slower** — the GPU against the CPU — 1499 s on the CPU, 1975 s on the GPU, three courses at a time The two parsers draw some trees differently, so the student reads some sentences into other frames and chooses another option there. «Same choice» counts the tests where both modes chose the same option, right or wrong. The GPU run is for training and bulk measurements; scores on the site come from the CPU. CPU run: 2026-10-22, commit `249ff72f1`; GPU run: 2026-10-22, commit `249ff72f1`. ## By course | course | tests | right, CPU | right, GPU | difference | same choice | time, CPU | time, GPU | | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | | [Adult life](https://md.mova.elamur.ai/free/en/school-run/adult-life/) | 689 | 35.4% | 35.3% | -1 | 82.3% | 6 s | 10 s | | [AI](https://md.mova.elamur.ai/free/en/school-run/ai/) | 331 | 40.8% | 41.4% | +2 | 89.4% | 3 s | 7 s | | [Arts](https://md.mova.elamur.ai/free/en/school-run/arts/) | 477 | 36.3% | 38.4% | +10 | 87.2% | 3 s | 7 s | | [Biology](https://md.mova.elamur.ai/free/en/school-run/biology/) | 4581 | 49.1% | 49.6% | +23 | 78.9% | 51 s | 65 s | | [Books](https://md.mova.elamur.ai/free/en/school-run/books/) | 24316 | 30.5% | 31.0% | +123 | 67.9% | 1263 s | 1630 s | | [Chemistry](https://md.mova.elamur.ai/free/en/school-run/chemistry/) | 392 | 50.5% | 50.8% | +1 | 81.6% | 6 s | 6 s | | [Chinese street](https://md.mova.elamur.ai/free/en/school-run/chinese-street/) | 353 | 39.9% | 41.6% | +6 | 74.8% | 4 s | 5 s | | [English](https://md.mova.elamur.ai/free/en/school-run/english/) | 666 | 30.8% | 34.4% | +24 | 78.8% | 6 s | 9 s | | [Euphemisms](https://md.mova.elamur.ai/free/en/school-run/euphemisms/) | 521 | 39.2% | 38.6% | -3 | 90.4% | 4 s | 7 s | | [Everyday](https://md.mova.elamur.ai/free/en/school-run/everyday/) | 7211 | 46.8% | 46.1% | -56 | 79.8% | 77 s | 115 s | | [French](https://md.mova.elamur.ai/free/en/school-run/french/) | 468 | 38.0% | 37.6% | -2 | 85.0% | 5 s | 5 s | | [Geography](https://md.mova.elamur.ai/free/en/school-run/geography/) | 699 | 46.4% | 46.5% | +1 | 84.8% | 5 s | 8 s | | [History](https://md.mova.elamur.ai/free/en/school-run/history/) | 960 | 44.4% | 45.4% | +10 | 85.1% | 7 s | 10 s | | [Language](https://md.mova.elamur.ai/free/en/school-run/language/) | 602 | 36.0% | 36.5% | +3 | 79.7% | 5 s | 8 s | | [Medicine](https://md.mova.elamur.ai/free/en/school-run/medicine/) | 858 | 42.2% | 44.5% | +20 | 88.6% | 5 s | 8 s | | [Money](https://md.mova.elamur.ai/free/en/school-run/money/) | 469 | 37.7% | 37.7% | +0 | 85.7% | 4 s | 7 s | | [Myths](https://md.mova.elamur.ai/free/en/school-run/myths/) | 389 | 46.0% | 48.1% | +8 | 85.9% | 3 s | 6 s | | [Physics](https://md.mova.elamur.ai/free/en/school-run/physics/) | 483 | 51.1% | 49.3% | -9 | 87.4% | 4 s | 6 s | | [Politics](https://md.mova.elamur.ai/free/en/school-run/politics/) | 475 | 41.1% | 44.2% | +15 | 81.7% | 4 s | 7 s | | [Reflection](https://md.mova.elamur.ai/free/en/school-run/reflection/) | 340 | 43.5% | 41.2% | -8 | 86.8% | 4 s | 6 s | | [Religion ethics](https://md.mova.elamur.ai/free/en/school-run/religion-ethics/) | 1141 | 43.4% | 43.8% | +5 | 81.2% | 10 s | 13 s | | [Space](https://md.mova.elamur.ai/free/en/school-run/space/) | 357 | 42.6% | 44.5% | +7 | 83.8% | 3 s | 4 s | | [Technology](https://md.mova.elamur.ai/free/en/school-run/technology/) | 481 | 56.3% | 57.2% | +4 | 89.0% | 5 s | 7 s | | [Ukrainian street](https://md.mova.elamur.ai/free/en/school-run/ukrainian-street/) | 357 | 37.3% | 37.5% | +1 | 80.4% | 3 s | 5 s | | [World](https://md.mova.elamur.ai/free/en/school-run/world/) | 2019 | 42.1% | 42.5% | +9 | 84.2% | 9 s | 14 s | How the modes are built and gated: [GPU execution](https://md.mova.elamur.ai/free/en/docs/repo-docs/gpu-exec/).