Within General Capability, model spread concentrates in competition mathematics (AIME), which dominates the aggregate score¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Per-year AIME success ranges from above 90% for the strongest models to the thirties and fifties for others, a wider range than any other general component. → Yilin Jiang 2026

Evidence¶

Yilin Jiang 2026¶

Yilin Jiang, Xiaorong Zhu, Fei Tan, Zicheng Zhang, Kaiyi Huang, Yang Yu, Zexuan Fei, Yiming Luo, Keqian Li, Hao Hao, Guangtao Zhai, Aimin Zhou. (2026). ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models. https://arxiv.org/abs/2608.09548 doi:10.48550/arxiv.2608.09548

q2 · i? · design · r2

Per-component General Capability results (Figure 3, Appendix A Table 4) for the nine-model evaluation. Easier components are near ceiling; the article states the aggregate is dominated by competition mathematics, so two models can differ by roughly ten points almost entirely because of AIME. InnoSpark-235B scores 85.1% on C-Eval but 13.3–20.0% across the three AIME years.

"On AIME (2024–2026), per-year success ranges from above 90%for the strongest models to the thirties and fifties for others on the same problems, a wider range than any other general component."

Discussion¶

Related Claims¶

• The top six models are statistically indistinguishable on overall ELBench score yet differ substantially at the module level, so module profiles are more informative than a single aggregate — related
• Over a quarter of benchmark tasks (23 of 80) defeat all six frontier models, with over 22% showing capability boundaries where scores swing by up to 90 points — related
• Task category is the dominant factor in agent performance: cross-category spread (26.3 points) far exceeds cross-model spread (8.8 points) — related