AIME 2026
American Invitational Mathematics Examination 2026 problems.
Models ranked
18
tracked on this benchmark
Score band
99.2 – 37.5
best → lowest tracked
Snapshot trend
+6.73
Oct 9 → Oct 13 · 1 models
Leaderboard
Tracked models ranked by Score (higher is better).
Notes: Aleph Alpha first-party HF model card Aleph-Alpha/Kolibri-1 (FP8 release checkpoint), Evaluation > Post-training table; same value in launch blog/landing page. Harness: Aleph-Alpha-Research eval-framework (Harbor for TerminalBench/SWE-Bench), Kolibri at reasoning effort high, each model at its documented context window. BF16 repo card reports 96.7. AIME 2026 (DE) 90.0 not seeded. Self-reported by the lab.
Notes: Official Microsoft AI announcement result for MAI-Thinking-1.
Notes: Scores from the released-checkpoint "after" table on the Hugging Face model card.
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Jun 2, 2026