Best for math

Ranked by Epoch's mock AIME 2024-2025 (competition mathematics). Source: Epoch AI. Variants (reasoning effort, batch) are folded into one row.

#	Model	Capability	AA index	Reasoning	Math	Coding	Context	$/M	Weights	Released
1	DDeepSeek V4 Pro 0813DeepSeek	155.4	36.0	91.7	98.6	—	1.05M	$1.41	Open	13 Aug 2026
2	MKimi K3Moonshot AI · +1 variant	157.7	43.6	93.1	97.2	68.5	1.05M	$6.00	Open	16 Jul 2026
3	DDeepSeek V4 Flash 0731DeepSeek	154.5	34.3	91.0	94.4	—	1.31M	$0.093	Open	31 Jul 2026
4	ZGLM 5.3 FlashZ.ai (Zhipu AI)	151.9	41.8	90.2	93.9	63.4	1.31M	$0.24	Open	20 Aug 2026
5	ZGLM 5.3Z.ai (Zhipu AI)	155.6	44.8	90.9	91.1	69.0	1.31M	$2.15	Open	14 Aug 2026
6	TInkling SmallxhighThinking Machines Lab	—	—	88.5	90.0	—	—	—	Open	15 Jul 2026
7	TInklingxhighThinking Machines Lab	—	—	88.3	88.9	—	—	—	Open	15 Jul 2026

• AClaude Sonnet 5.5
  Anthropic · 28 Sep 2026 · AA 56 · 1M · $4.00/M
• AQwen3.8 Max Prime
  Alibaba (Qwen) · 23 Sep 2026 · 1M · $6.00/M
• OGPT-6 Sol
  OpenAI · 22 Sep 2026 · AA 47.5 · 1.05M · $4.00/M
• OGPT-6 Luna
  OpenAI · 22 Sep 2026 · AA 37.3 · 1.05M · $0.20/M
• OGPT-6 Sol Pro
  OpenAI · 22 Sep 2026 · 1.05M · $4.00/M
• OGPT-6 Luna Pro
  OpenAI · 22 Sep 2026 · 1.05M · $0.20/M
• AClaude Opus 5.5
  Anthropic · 22 Sep 2026 · AA 57.6 · 1M · $8.00/M
• XGrok 4.7
  xAI · 21 Sep 2026 · AA 46.4 · 500K · $3.00/M

Not ranked until an independent evaluator (Epoch AI) publishes scores. We don't use vendor-reported benchmark claims for rankings.