Skip to main content
BenchLM
Advertise

Benchmark profile

AIME 2026 (AIME26)

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

Data verified

Top models on AIME26 — July 23, 2026

As of July 23, 2026, GLM-5.2 leads the AIME26 leaderboard with 99.2% , followed by Inkling (97.1%) and Kimi K2.6 (96.4%).

1Open

GLM-5.2

Z.AI

glm-5-2

99.2%
Overall 63.96Context 1M
2Open

Inkling

Thinking Machines Lab

inkling

97.1%
Overall 67.54Context 1M
3Open

Kimi K2.6

Moonshot AI

kimi-2-6

96.4%
Overall 56.79Context 256K
17 modelsMath25% of category scoreCurrentUpdated July 23, 2026

Leaderboard (17 models)

Score
1
GLM-5.2Z.AI · Open weight
99.2%
2
InklingThinking Machines Lab · Open weight
97.1%
3
Kimi K2.6Moonshot AI · Open weight
96.4%
4
GLM-5Z.AI · Open weight
95.8%
5
Kimi K2.5Moonshot AI · Open weight
95.8%
6
GLM-5.1Z.AI · Open weight
95.3%
7
Qwen3.6 PlusAlibaba · Closed
95.3%
8
Claude Opus 4.5Anthropic · Closed
95.1%
9
MAI-Thinking-1Microsoft · Closed
94.5%
10
Qwen3.6-27BAlibaba · Open weight
94.1%
11
Qwen3.5 397BAlibaba · Open weight
93.3%
12
Qwen3.6-35B-A3BAlibaba · Open weight
92.7%
13
ZAYA1-8BZyphra · Open weight
89.1%
14
Gemma 4 12BGoogle · Open weight
77.5%
15
ZAYA1-74B-PreviewZyphra · Open weight
76.4%
16
LFM2.5-8B-A1BLiquidAI · Open weight
50.0%
17
MiniCPM5-1BOpenBMB · Open weight
40.4%

According to BenchLM.ai, GLM-5.2 leads the AIME26 benchmark with a score of 99.2%, followed by Inkling (97.1%) and Kimi K2.6 (96.4%). The top models are clustered within 2.8 points, suggesting this benchmark is nearing saturation for frontier models.

17 models have been evaluated on AIME26. The benchmark falls in the Math category. This category carries a 5% weight in BenchLM.ai's overall scoring system. Within that category, AIME26 contributes 25% of the category score, so strong performance here directly affects a model's 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

BenchLM freshness & 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.

FAQ

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?

17 AI models have been evaluated on AIME26 on BenchLM.

Compare Top Models on AIME26

GLM-5.2 vs InklingInkling vs Kimi K2.6Kimi K2.6 vs GLM-5GLM-5 vs Kimi K2.5
Last updated: July 23, 2026 · BenchLM version AIME26 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.