Spark-X2.6 Release - ClawEval-EN: leaderboard
Spark-X 2.6 official release SVG; own unstarred evaluations only, source-starred reprints and missing cells not duplicated. All runs thinking; Spark-X 2.6 explicitly high, recommended temperature 1/top_p 0.95/top_k-1. Other models remain thinking with effort unspecified. Gemma 4-12B label is source-scoped because exact checkpoint is not identified; never aliased to Gemma 3/4 or inferred weights. Gaokao 2026 averages five Chinese exams, each 150 points; other source benchmark scores retain native 0–100 units. No undocumented decoding/harness assumed. Metric: Score (%)
Metric: Score (%). Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Spark-X2.6-4B (High) | 69.9 | |
| 2 | Spark-X2.5-4B (Thinking) | 66.2 | |
| 3 | Spark-X2.6 Release Gemma4-12B (checkpoint unspecified) (Thinking) | 58.3 |
Interactive version: theaggregate.ai/benchmark?slug=spark-x2-6-release-claweval-en · How It Works · Data refreshed daily, snapshot 2026-11-05.