# AIME26 leaderboard

Mathematics benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/math-aime2026

AIME 2026. Every model the catalog carries a published AIME26 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Mathematics |
| Measure | Short-answer mathematics |
| Tasks | Competition math problems |
| Difficulty | Olympiad-style mathematics |
| Published by | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |

A 2026 American Invitational Mathematics Examination snapshot used in frontier-model comparison tables for mathematical reasoning.

## AIME26 ranking

34 models with a published AIME26 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Short-answer mathematics | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | 99.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Beam 1.0 501B-A23B FP8](https://modelscale.dev/models/reflection-beam-fp8) | Reflection AI | 98.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Beam 1.0 501B-A23B](https://modelscale.dev/models/reflection-beam) | Reflection AI | 97.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Beam 1.0 501B-A23B NVFP4](https://modelscale.dev/models/reflection-beam-nvfp4) | Reflection AI | 97.5 | Observed 2026-11-21 · source benchlm:models |
| 5 | [A.X K2](https://modelscale.dev/models/a-x-k2) | SK Telecom | 97.1 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 97.1 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 96.4 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Ternary Bonsai 2 27B](https://modelscale.dev/models/ternary-bonsai-2-27b) | Prism ML | 95.8 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GLM-5](https://modelscale.dev/models/glm-5) | Z.AI | 95.8 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 95.8 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Solar Open 2](https://modelscale.dev/models/solar-open-2) | Upstage | 95.7 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | 95.5 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | 95.3 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 95.3 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Solar Pro 4](https://modelscale.dev/models/solar-pro-4) | Upstage | 95.3 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 95.1 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Ripple-65B Preview](https://modelscale.dev/models/ripple-65b-preview) | Ricursive Intelligence | 95.0 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | 94.7 | Observed 2026-11-21 · source benchlm:models |
| 19 | [MAI-Thinking-1](https://modelscale.dev/models/mai-thinking-1) | Microsoft | 94.5 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | 94.1 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 93.3 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Ling 3.0 Flash](https://modelscale.dev/models/ling-3-0-flash) | InclusionAI | 93.2 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 92.7 | Observed 2026-11-21 · source benchlm:models |
| 24 | [K-EXAONE 2.0](https://modelscale.dev/models/k-exaone-2-0) | LG AI Research | 92.3 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Spark-X2.6-4B](https://modelscale.dev/models/spark-x2-6-4b) | SparkLLM | 91.2 | Observed 2026-11-21 · source benchlm:models |
| 26 | [MiniMax M2.7](https://modelscale.dev/models/minimax-m2-7) | MiniMax | 89.8 | Observed 2026-11-21 · source benchlm:models |
| 27 | [ZAYA1-8B](https://modelscale.dev/models/zaya1-8b) | Zyphra | 89.1 | Observed 2026-11-21 · source benchlm:models |
| 28 | [MiniCPM5-2B](https://modelscale.dev/models/minicpm5-2b) | OpenBMB | 86.5 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Gemma 4 12B](https://modelscale.dev/models/gemma-4-12b) | Google | 77.5 | Observed 2026-11-21 · source benchlm:models |
| 30 | [ZAYA1-74B-Preview](https://modelscale.dev/models/zaya1-74b-preview) | Zyphra | 76.4 | Observed 2026-11-21 · source benchlm:models |
| 31 | [LongCat-Flash-Lite-Sparse](https://modelscale.dev/models/longcat-flash-lite-sparse) | Meituan | 65.7 | Observed 2026-11-21 · source benchlm:models |
| 32 | [LFM2.5-8B-A1B](https://modelscale.dev/models/lfm2-5-8b-a1b) | LiquidAI | 50.0 | Observed 2026-11-21 · source benchlm:models |
| 33 | [MiniCPM5-1B](https://modelscale.dev/models/minicpm5-1b) | OpenBMB | 40.4 | Observed 2026-11-21 · source benchlm:models |
| 34 | [LLaDA2.2-mini](https://modelscale.dev/models/llada2-2-mini) | InclusionAI | 35.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
