TensorBench - Codegen: leaderboard

Metric: Pass rate (%) on the 7 code-generation tasks (OpenMP and atomic-scatter parallelism, SIMD vectorization, CUDA and out-of-core backends); each coding agent (a published CLI scaffold with its model) edits the open-source Scorch compiler-based tensor framework inside a per-task container, one run per task; a task passes when every test of the post-patch suite (pre-existing randomized regression tests plus the tests the agent adds) succeeds; higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 7 models tracked.

Top models

#ModelScore
1Claude Opus 4.7 (xHigh)71.4
2Claude Opus 4.657.1
3GPT-5.5 (xHigh)57.1
4GPT-5.3 Codex (xHigh)42.9
5Gemini 3.1 Pro (Preview)28.6
6GPT-5.4 (xHigh)14.3
7Qwen 3 Coder 480B A35B Instruct14.3

Interactive version: theaggregate.ai/benchmark?slug=tensorbench-codegen · How It Works · Data refreshed daily, snapshot 2026-09-29.