AIME 2026 benchmark

20 AI models ranked on AIME 2026. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.

Top model today

Inkling (Thinking Machines) leads at 97%, from $0.95 per 1M input via DeepInfra.

Data via MathArena →

Models ranked

on this benchmark

Top score

97%

current leader

Type

Single eval

benchmark

Updated

Oct 14, 2026

benchmark scores

Cost vs AIME 2026

15 priced models

Most attractive quadrant (cheap + high)

= reasoning model (extended thinking)

Each labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.

Models ranked on AIME 2026

highest score first · 20 models

Maker

#
1	Inkling	Thinking Machines	97%	$0.95 via DeepInfra	$4.05 via Baseten
2	A.X-K2	Sk-telecom	97%	n/a	n/a
3	Step 3.5 Flash	Other	97%	$0.09 Routed quote	$0.30 Routed quote
4	Kimi K2.6	Moonshot	96%	$0.65 via Wandb	$3.40 via Novita
5	Kimi K2.5	Moonshot	96%	$0.45 via DeepInfra	$2.25 via DeepInfra
6	GLM 5	Zhipu	96%	$0.60 via DeepInfra	$1.92 Routed quote
7	inclusionAI: Ring-2.6-1T	Other	96%	n/a	n/a
8	Solar Open2 250B	Upstage	96%	n/a	n/a
9	Inkling Small	Thinking Machines	96%	$0.45 via DeepInfra	$1.20 via Baseten
10	GLM 5.1	Zhipu	95%	$1.05 via DeepInfra	$3.50 via DeepInfra
11	Muse Glimmer 30B	Other	95%	$0.30 via DeepInfra	$1.20 via DeepInfra
12	Qwen3.6 27B	Alibaba	94%	$0.15 via Libertai	$0.50 via Libertai
13	Qwen3.5 397B A17B	Alibaba	93%	$0.164 via Aihubmix	$0.986 via Aihubmix
14	inclusionAI: Ling 3.0 Flash	Other	93%	$0.021 Routed quote	$0.063 Routed quote
15	Qwen3.6 35B A3B	Alibaba	93%	$0.05 via Sail	$0.40 via Sail
16	EXAONE 4.5 33B	Lg-ai-research	93%	n/a	n/a
17	Qwen3.5-27B	Alibaba	91%	$0.26 via DeepInfra	$2.40 via Novita
18	Nemotron 3 120B A12b	NVIDIA	90%	$0.50 via Cloudflare	$1.50 via Cloudflare
19	Qwen3 30B A3b Thinking 2507	Alibaba	88%	$0.20 Routed quote	$0.90 via Fireworks AI
20	inclusionAI: Ling-2.6-flash	Other	74%	n/a	n/a

On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.

Frequently asked questions

What is the AIME 2026 benchmark?

The 2026 American Invitational Mathematics Examination (AIME I and II), used as a maths benchmark on problems released after most models' training cutoffs. Each contest is 15 integer-answer problems, scored on accuracy.

Which AI model scores highest on AIME 2026?

Inkling (Thinking Machines) leads with 97%, from $0.95 per 1M input tokens from DeepInfra.

How many models are ranked on AIME 2026?

20 models carry an AIME 2026 score. Scores come from Hugging Face leaderboards; where a model has a listed API price it is drawn from LiteLLM and OpenRouter, and models with no current price are listed without one.

Other benchmarks

compare the same models on a different eval

Benchmark scores via Hugging Face leaderboards · scores updated Oct 14, 2026 · Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 8 prices older, back to Sep 15, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI