Axis Spatial - GS-QA2: leaderboard

Axis Spatial's GS-QA2 cohort evaluates spatial database reasoning over 221 questions, averaged within templates under methodology 1.0. Every entry preserves its own model effort and agent harness, with one scored attempt per task and a two-hour limit. Code checks grade files and numerical/geometry outputs; Claude Sonnet 5.5 grades maps and traces where needed. Scores use the source's attempted/scored population, including its pending-trace policy; missing attempts are not zeros. These are adapted evaluator runs, not reproductions of the original papers.

Metric: Template-macro pass@1 (%). Source: www.axisspatial.com. Saturation forecast: Rough model projection: around 2026. 83 models tracked.

Top models

#ModelScoreOverall rank
1GPT-5.6 Sol (Medium) (Axis Spatial Run: native=codex-gpt-5-6-sol-medium; cfg=29380bbd8c1a5009)100
2Claude Opus 5.5 (xHigh) (Axis Spatial Run: native=claude-code-claude-opus-5-5-xhigh; cfg=b2f9ca8815f8e318)94.35
3GPT-6.1 Sol (xHigh) (Axis Spatial Run: native=codex-gpt-6-1-sol-xhigh; cfg=3801b72ee5f0ebfa)94.35
4GPT-6.1 Sol (Medium) (Axis Spatial Run: native=codex-gpt-6-1-sol-medium; cfg=be21af26b13cb8e8)93.37
5GPT-6.1 Sol (High) (Axis Spatial Run: native=codex-gpt-6-1-sol-high; cfg=b35d923d12600043)92.59
6Claude Sonnet 5.5 (Max) (Axis Spatial Run: native=claude-code-claude-sonnet-5-5-max; cfg=1563014b684c3134)91.97
7Claude Opus 5.5 (Max) (Axis Spatial Run: native=claude-code-claude-opus-5-5-max; cfg=64f5831c15f78626)91.5
8Claude Opus 5 (High) (Axis Spatial Run: native=claude-code-claude-opus-5-high; cfg=beb735020b8f0d3d)91.09
9Claude Opus 5.5 (Medium) (Axis Spatial Run: native=claude-code-claude-opus-5-5-medium; cfg=63bfc558f73f4da3)90.27
10Claude Opus 5.5 (High) (Axis Spatial Run: native=claude-code-claude-opus-5-5-high; cfg=4142b177c8511092)89.93

Interactive version: theaggregate.ai/benchmark?slug=axis-spatial-gs-qa2 · How It Works · Data refreshed daily, snapshot 2026-11-05.