AIME 2025
American Invitational Mathematics Examination 2025 problems
Models ranked
34
tracked on this benchmark
Score band
98.4 – 14.0
best → lowest tracked
Snapshot trend
+1.60
Aug 7 → Oct 6 · 1 models
Leaderboard
Tracked models ranked by Score (higher is better).
Notes: Official Microsoft AI announcement result for MAI-Thinking-1.
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 95.8. AIME 2025 (DE) 87.5 not seeded. Self-reported by the lab.
Configuration: HyperNova 60B 2605 weights; reasoning effort high; vLLM 0.13.0; temp 1.0, top_p 1.0
Notes: First-party model card table 'HyperNova 60B Benchmark Comparison' (card last modified 2026-08-07); same numbers in Multiverse article 'HyperNova 60B v2605' section (updated 2026-06-17).
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: May 20, 2026