AIME26 leaderboard
Rank	Model / configuration	Score	Parameters (B)	Open / closed
1	GLM-5.2Z.AI	99.2%	Not reported	Open
2	BeamReflection AI	97.8%	Not reported	Pending
3	InklingThinking Machines Lab	97.1%	Not reported	Open
4	A.X K2SK Telecom	97.1%	Not reported	Open
5	Kimi K2.6Moonshot AI	96.4%	Not reported	Open
6	Ternary Bonsai 2 27BPrism ML	95.8%	Not reported	Open
7	GLM-5Z.AI	95.8%	Not reported	Open
8	Kimi K2.5Moonshot AI	95.8%	Not reported	Open
9	Solar Open 2Upstage	95.7%	Not reported	Open
10	Inkling-SmallThinking Machines Lab	95.5%	Not reported	Open
11	GLM-5.1Z.AI	95.3%	Not reported	Open
12	Qwen3.6 PlusAlibaba	95.3%	Not reported	Closed
13	Solar Pro 4Upstage	95.3%	Not reported	Closed
14	Claude Opus 4.5Anthropic	95.1%	Not reported	Closed
15	Muse Glimmer 30BMeta	94.7%	Not reported	Open
16	MAI-Thinking-1Microsoft	94.5%	Not reported	Closed
17	Qwen3.6-27BAlibaba	94.1%	Not reported	Open
18	Qwen3.5 397BAlibaba	93.3%	Not reported	Open
19	Ling 3.0 FlashInclusionAI	93.2%	Not reported	Open
20	Qwen3.6-35B-A3BAlibaba	92.7%	Not reported	Open
21	K-EXAONE 2.0LG AI Research	92.3%	Not reported	Open
22	ZAYA1-8BZyphra	89.1%	Not reported	Open
23	MiniCPM5-2BOpenBMB	86.5%	Not reported	Open
24	Gemma 4 12BGoogle	77.5%	Not reported	Open
25	ZAYA1-74B-PreviewZyphra	76.4%	Not reported	Open
26	LongCat-Flash-Lite-SparseMeituan	65.7%	Not reported	Open
27	LFM2.5-8B-A1BLiquidAI	50.0%	Not reported	Open
28	MiniCPM5-1BOpenBMB	40.4%	Not reported	Open
29	LLaDA2.2-miniInclusionAI	35.0%	Not reported	Open

According to BenchLM.ai, GLM-5.2 leads the AIME26 benchmark with a score of 99.2%, followed by Beam (97.8%) and Inkling (97.1%). The top models are clustered within 2.1 points, suggesting this benchmark is nearing saturation for frontier models.

29 models have been evaluated on AIME26. The benchmark falls in the Mathematics category. The Mathematics leaderboard ranks models by a weighted category score, and AIME26 contributes 25% of it. BenchAlign v5.8 also uses it in the overall ranking.

About AIME26

Year

2026

Tasks

Competition math problems

Format

Short-answer mathematics

Difficulty

Olympiad-style mathematics

AIME-style benchmarks remain one of the fastest ways to separate top reasoning models on olympiad-style math. AIME 2026 is a newer contest-year snapshot than the legacy AIME rows already tracked on BenchLM.

Qwen3.6 launch benchmarks

Freshness and provenance

Version

AIME26 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

Current

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does AIME26 measure?

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

Which model scores highest on AIME26?

GLM-5.2 by Z.AI currently leads with a score of 99.2% on AIME26.

How many models are evaluated on AIME26?

29 AI models have published results on AIME26 in the BenchLM catalog.

Compare top models on AIME26

GLM-5.2 vs Beam Beam vs Inkling Inkling vs A.X K2 A.X K2 vs Kimi K2.6

Last updated: October 7, 2026 · BenchLM version AIME26 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 5,500+ readers.

One email each week. Unsubscribe anytime.