Independent model evidence

LLM Leaderboard

Published capability scores, source-native Arena rankings, benchmark results, specifications and pricing. Each signal stays separate so the evidence remains inspectable.

Data as of 2026-08-07

View overall ranking Compare models

Published models297Model families

Task charts4Published result sets

Scored models170Latest scored version per model

Text Arena rows3,856Published results

The latest scored version of each unique model, grouped into three readable performance bands.

LeadersTop signal band

GPT-5.6-Sol96.5 Qwen3.7 Max90.3 Seed 2.1 Pro87.4 GPT-5.6-Terra85.4

High performersStrong evidence

Gemini 3.1 Pro84.3 Claude Opus 4.882.9 Kimi K2.682.8 Gemini 3 Pro82.2 Seed 2.1 Turbo80.5 GLM 5.280.3 Hy380.1 DeepSeek-V4-Pro80.1 Claude Opus 4.778.4 Gemini 2.5 Pro78.0 GPT-5.6-Luna77.2 GPT-5.576.8 GPT-5.475.6 DeepSeek-V3.275.5 Qwen3.5 397B A17B75.2 Nova 2 Pro75.1

LLMBoard scoreOfficial API price blend (8:1 input/output), USD / 1M

Efficient frontier62 models with official PAYG prices

Reasoning: GPQA

Coding: SWE-Bench Verified

Math: AIME 2025

Speech-to-Text: FLEURS


1	OPGPT-5.6-SolOpenAI	GPT-5.6 Sol	96.5	99.8	96.5	100.0	86.2	100.0	100.0%	1.1M	Closed weights	$5	$30	94.6%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	90.4%	N/A
2	ACQwen3.7 MaxAlibaba Cloud / Qwen Team	Qwen3.7 Max	90.3	91.8	N/A	93.1	83.8	93.0	80.0%	1M	Closed weights	$2.5	$7.5	92.4%	89.6%	N/A	N/A	N/A	N/A	N/A	94.3%	N/A	N/A
3	BYSeed 2.1 ProByteDance	Seed 2.1 Pro	87.4	N/A	87.7	N/A	84.4	90.9	60.0%	N/A	Closed weights	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	86.2%	N/A
4	OPGPT-5.6-TerraOpenAI	GPT-5.6 Terra	85.4	96.1	93.0	93.8	58.3	82.5	100.0%	1.1M	Closed weights	$2	$12	92.9%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	87.5%	N/A
5	GOGemini 3.1 ProGoogle	Gemini 3.1 Pro	84.3	99.1	86.0	N/A	78.5	65.2	80.0%	1M	Closed weights	$2	$12	94.3%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	85.9%	N/A
6	ANClaude Opus 4.8Anthropic	Claude Opus 4.8	82.9	98.1	78.9	N/A	84.9	60.0	80.0%	1M	Closed weights	$5	$25	93.6%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	84.3%	N/A
7	MAKimi K2.6Moonshot AI	Kimi K2.6	82.8	92.2	89.5	61.9	76.8	93.8	100.0%	262.1K	Open weights	$0.95	$4	90.5%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	86.3%	N/A
8	GOGemini 3 ProGoogle	Gemini 3 Pro	82.2	93.5	N/A	N/A	72.7	76.0	60.0%	1M	Closed weights	N/A	N/A	91.9%	N/A	100.0%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
9	BYSeed 2.1 TurboByteDance	Seed 2.1 Turbo	80.5	N/A	84.2	N/A	73.7	84.8	60.0%	N/A	Closed weights	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	84.9%	N/A
10	ZAGLM 5.2Zhipu AI	GLM-5.2	80.3	92.7	N/A	84.7	45.7	100.0	80.0%	1M	Open weights	N/A	N/A	91.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
11	TEHy3Tencent	Hy3	80.1	91.4	77.2	86.1	63.0	N/A	80.0%	256K	Open weights	N/A	N/A	90.4%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	84.2%	N/A
12	DEDeepSeek-V4-ProDeepSeek	DeepSeek-V4-Pro-Max	80.1	90.1	71.9	83.9	65.2	89.2	100.0%	1M	Closed weights	N/A	N/A	90.1%	87.5%	N/A	N/A	93.5%	N/A	N/A	N/A	83.4%	N/A
13	ANClaude Opus 4.7Anthropic	Claude Opus 4.7	78.4	98.7	65.8	N/A	55.8	91.7	80.0%	1M	Closed weights	$5	$25	94.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	79.3%	N/A
14	GOGemini 2.5 ProGoogle	Gemini 2.5 Pro Preview 06-05	78.0	81.0	N/A	N/A	82.3	67.1	60.0%	1M	Closed weights	N/A	N/A	86.4%	N/A	88.0%	N/A	69.0%	N/A	N/A	N/A	N/A	N/A
15	OPGPT-5.6-LunaOpenAI	GPT-5.6 Luna	77.2	94.0	70.2	87.5	56.4	72.5	100.0%	1.1M	Closed weights	$0.20	$1.2	92.3%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	83.3%	N/A
16	OPGPT-5.5OpenAI	GPT-5.5	76.8	98.1	80.7	62.5	71.2	62.5	100.0%	1.1M	Closed weights	$5	$30	93.6%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	84.4%	N/A
17	OPGPT-5.4OpenAI	GPT-5.4	75.6	95.7	68.4	81.3	53.9	73.3	100.0%	1.1M	Closed weights	$2.5	$15	92.8%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	82.7%	N/A
18	DEDeepSeek-V3.2DeepSeek	DeepSeek-V3.2-Speciale	75.5	N/A	N/A	93.8	51.6	83.2	60.0%	131.1K	Closed weights	N/A	N/A	N/A	N/A	96.0%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
19	ACQwen3.5 397B A17BAlibaba Cloud / Qwen Team	Qwen3.5-397B-A17B	75.2	94.1	75.0	54.5	68.9	79.9	100.0%	262.1K	Open weights	$0.43	$2.58	88.4%	87.8%	N/A	N/A	N/A	N/A	N/A	92.6%	69.0%	N/A
20	AMNova 2 ProAmazon	Nova 2 Pro	75.1	67.0	N/A	N/A	80.6	81.4	60.0%	N/A	Closed weights	N/A	N/A	81.4%	81.6%	92.3%	N/A	74.6%	N/A	N/A	N/A	N/A	N/A
21	GOGemma 4 31BGoogle	Gemma 4 31B	74.3	75.0	N/A	N/A	71.7	76.5	60.0%	262.1K	Open weights	N/A	N/A	84.3%	85.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
22	ANClaude Sonnet 3.5Anthropic	Claude 3.5 Sonnet	73.4	41.4	N/A	84.9	96.9	80.4	80.0%	200K	Closed weights	N/A	N/A	67.2%	77.6%	N/A	90.4%	N/A	78.3%	93.7%	N/A	N/A	N/A
23	ACQwen3.7 PlusAlibaba Cloud / Qwen Team	Qwen3.7-Plus	73.1	84.1	N/A	66.9	54.0	88.2	80.0%	1M	Closed weights	$0.50	$3	90.3%	88.5%	N/A	N/A	N/A	N/A	N/A	94.6%	N/A	N/A
24	GOGemini 3 FlashGoogle	Gemini 3 Flash	72.6	91.4	N/A	N/A	51.9	68.8	60.0%	1M	Closed weights	$0.50	$3	90.4%	N/A	99.7%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
25	ACQwen3.6 PlusAlibaba Cloud / Qwen Team	Qwen3.6 Plus	72.4	79.0	N/A	67.4	62.8	80.9	80.0%	1M	Closed weights	$0.50	$3	90.4%	88.5%	N/A	N/A	N/A	N/A	N/A	94.3%	N/A	N/A
26	ACQwen3.6 27BAlibaba Cloud / Qwen Team	Qwen3.6-27B	72.2	84.5	N/A	45.5	80.8	75.9	80.0%	262.1K	Open weights	N/A	N/A	87.8%	86.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
27	NVNemotron 3 UltraNVIDIA	Nemotron 3 Ultra (550B A55B)	72.1	82.5	15.8	100.0	76.1	87.4	100.0%	1M	Open weights	N/A	N/A	87.0%	86.8%	N/A	N/A	N/A	N/A	N/A	N/A	44.4%	N/A
28	DEDeepSeek-V4-FlashDeepSeek	DeepSeek-V4-Flash-Max	71.7	86.4	52.6	76.1	68.3	71.5	100.0%	1M	Closed weights	N/A	N/A	88.1%	86.2%	N/A	N/A	91.6%	N/A	N/A	N/A	73.2%	N/A
29	MAKimi K2.5Moonshot AI	Kimi K2.5	71.6	84.1	56.1	58.9	70.6	89.7	100.0%	262.1K	Open weights	$0.60	$3	87.6%	87.1%	96.1%	N/A	N/A	N/A	N/A	N/A	74.9%	N/A
30	OPGPT-5OpenAI	GPT-5	71.6	79.3	33.3	61.5	97.7	88.4	100.0%	400K	Closed weights	$1.25	$10	85.7%	N/A	94.6%	92.5%	N/A	84.7%	93.4%	N/A	54.9%	N/A
31	MELlama 3.1 405BMeta	Llama 3.1 405B Instruct	69.9	61.2	N/A	76.5	87.7	52.0	80.0%	128K	Closed weights	N/A	N/A	50.7%	73.3%	N/A	87.3%	N/A	73.8%	89.0%	88.6%	N/A	N/A
32	DEDeepSeek-V2.5DeepSeek	DeepSeek-V2.5	69.5	N/A	N/A	69.4	75.4	62.0	60.0%	8.2K	Closed weights	N/A	N/A	N/A	N/A	N/A	80.4%	N/A	74.7%	89.0%	N/A	N/A	N/A
33	ANClaude Opus 4.6Anthropic	Claude Opus 4.6	69.2	93.1	75.4	N/A	24.1	81.3	80.0%	1M	Closed weights	$5	$25	91.3%	N/A	99.8%	N/A	N/A	N/A	N/A	N/A	84.0%	N/A
34	OPGPT-5.2OpenAI	GPT-5.2	69.1	94.6	47.4	85.9	24.4	92.9	100.0%	400K	Closed weights	$1.75	$14	92.4%	N/A	100.0%	N/A	N/A	N/A	N/A	N/A	65.8%	N/A
35	XIMiMo V2.5 ProXiaomi	MiMo-V2.5-Pro	68.9	70.0	88.2	91.8	19.6	76.4	100.0%	1M	Open weights	$0.435	$0.87	66.7%	68.5%	N/A	89.4%	N/A	86.2%	N/A	N/A	N/A	N/A
36	GOGemma 4 26B A4BGoogle	Gemma 4 26B-A4B	67.2	68.8	N/A	N/A	67.5	64.2	60.0%	262.1K	Open weights	N/A	N/A	82.3%	82.6%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
37	XAGrok 4 FastxAI	Grok 4 Fast	66.2	79.3	17.5	64.1	88.9	82.1	100.0%	2M	Closed weights	N/A	N/A	85.7%	N/A	92.0%	N/A	80.0%	N/A	N/A	N/A	44.9%	N/A
38	ZAGLM 4.7Zhipu AI	GLM-4.7	66.2	79.3	49.1	38.9	82.7	81.4	100.0%	204.8K	Open weights	N/A	N/A	85.7%	84.3%	95.7%	N/A	N/A	N/A	N/A	N/A	52.0%	N/A
39	ACQwen3 235B A22B ThinkingAlibaba Cloud / Qwen Team	Qwen3-235B-A22B-Thinking-2507	65.7	66.4	N/A	58.3	61.6	79.9	80.0%	262.1K	Closed weights	N/A	N/A	81.1%	84.4%	92.3%	N/A	N/A	N/A	N/A	87.8%	N/A	N/A
40	ZAGLM 5.1Zhipu AI	GLM-5.1	64.7	80.6	65.8	59.5	34.1	84.4	100.0%	200K	Open weights	N/A	N/A	86.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	79.3%	N/A
41	ANClaude Sonnet 3.7Anthropic	Claude 3.7 Sonnet	63.6	76.7	N/A	56.5	N/A	51.3	60.0%	200K	Closed weights	N/A	N/A	84.8%	N/A	54.8%	N/A	N/A	N/A	N/A	93.2%	N/A	80.0%
42	GOGemini 2.5 FlashGoogle	Gemini 2.5 Flash	63.5	70.9	N/A	N/A	56.3	60.8	60.0%	1M	Closed weights	$0.30	$2.5	82.8%	N/A	72.0%	N/A	N/A	N/A	N/A	N/A	N/A	88.0%
43	AMNova ProAmazon	Nova Pro	63.5	55.0	N/A	74.2	52.7	77.9	80.0%	300K	Closed weights	$0.80	$3.2	46.9%	N/A	N/A	85.9%	N/A	76.6%	89.0%	92.1%	N/A	N/A
44	MIMAI Thinking 1Microsoft	MAI-Thinking-1	63.4	74.4	N/A	30.0	77.8	70.3	80.0%	N/A	Closed weights	N/A	N/A	84.2%	85.0%	97.0%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
45	OPo1OpenAI	o1	63.0	59.7	N/A	64.8	62.3	67.0	80.0%	200K	Closed weights	$15	$60	78.0%	N/A	N/A	91.8%	N/A	96.4%	88.1%	N/A	N/A	74.3%
46	NVLlama 3.3 Nemotron Super 49BNVIDIA	Llama-3.3 Nemotron Super 49B v1	62.6	39.7	N/A	64.5	96.9	52.5	80.0%	131.1K	Open weights	N/A	N/A	66.7%	N/A	58.4%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
47	NVLlama 3.1 Nemotron Ultra 253BNVIDIA	Llama 3.1 Nemotron Ultra 253B v1	62.6	57.3	N/A	75.8	66.7	48.1	80.0%	N/A	Closed weights	N/A	N/A	76.0%	N/A	72.5%	N/A	66.3%	N/A	N/A	89.5%	N/A	N/A
48	ZAGLM 4.5Zhipu AI	GLM-4.5	62.0	61.6	3.5	93.5	72.5	84.5	100.0%	131.1K	Open weights	N/A	N/A	79.1%	84.6%	N/A	N/A	72.9%	N/A	N/A	N/A	26.4%	91.0%
49	OPo3 miniOpenAI	o3-mini	61.6	58.4	N/A	56.3	69.8	62.8	80.0%	200K	Closed weights	$1.1	$4.4	77.2%	N/A	N/A	86.9%	N/A	97.9%	N/A	93.9%	N/A	87.3%
50	ACQwen3.5 122B A10BAlibaba Cloud / Qwen Team	Qwen3.5-122B-A10B	61.4	57.4	68.6	56.3	55.6	72.8	100.0%	262.1K	Open weights	N/A	N/A	86.6%	86.7%	N/A	N/A	N/A	N/A	N/A	93.4%	63.8%	N/A
51	MELongCat Flash ThinkingMeituan	LongCat-Flash-Thinking-2601	61.2	63.8	55.0	8.3	93.1	93.4	100.0%	128K	Closed weights	N/A	N/A	80.5%	N/A	99.6%	N/A	82.8%	N/A	N/A	N/A	56.6%	N/A
52	NVNemotron Nano 9BNVIDIA	Nemotron Nano 9B v2	61.2	34.5	N/A	87.1	75.0	52.9	80.0%	131.1K	Open weights	N/A	N/A	64.0%	N/A	72.1%	N/A	71.1%	N/A	N/A	90.3%	N/A	N/A
53	MAKimi K2 ThinkingMoonshot AI	Kimi K2-Thinking-0905	59.4	75.4	40.1	49.5	67.9	60.2	100.0%	262.1K	Closed weights	N/A	N/A	84.5%	84.6%	100.0%	N/A	N/A	N/A	N/A	N/A	60.2%	N/A
54	NVNemotron 3 SuperNVIDIA	Nemotron 3 Super (120B A12B)	59.1	70.3	7.0	78.1	69.4	70.7	100.0%	262.1K	Open weights	N/A	N/A	82.7%	83.7%	90.2%	N/A	81.2%	N/A	N/A	N/A	31.3%	N/A
55	ANClaude Opus 3Anthropic	Claude 3 Opus	58.8	59.3	N/A	60.5	46.2	72.7	80.0%	200K	Closed weights	N/A	N/A	50.4%	68.5%	N/A	86.8%	N/A	60.1%	84.9%	N/A	N/A	N/A
56	OPGPT-4.5OpenAI	GPT-4.5	58.8	44.0	N/A	93.6	46.7	53.0	80.0%	128K	Closed weights	N/A	N/A	69.5%	N/A	N/A	90.8%	N/A	N/A	88.0%	88.2%	N/A	36.7%
57	ACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen Team	Qwen3 VL 235B A22B Thinking	58.5	N/A	N/A	50.0	57.8	70.6	60.0%	262.1K	Closed weights	N/A	N/A	N/A	83.8%	89.7%	90.6%	N/A	N/A	N/A	88.2%	N/A	N/A
58	ACQwen3.5 27BAlibaba Cloud / Qwen Team	Qwen3.5-27B	57.1	66.8	37.3	59.4	52.9	69.9	100.0%	262.1K	Open weights	N/A	N/A	85.5%	86.1%	N/A	N/A	N/A	N/A	N/A	95.0%	61.0%	N/A
59	ACQwen2.5 32BAlibaba Cloud / Qwen Team	Qwen2.5 32B Instruct	56.9	30.0	N/A	81.7	68.3	53.6	80.0%	N/A	Closed weights	$0.70	$2.8	49.5%	69.0%	N/A	83.3%	N/A	83.1%	88.4%	N/A	N/A	N/A
60	OPGPT-OSS-120BOpenAI	GPT OSS 120B High	56.9	64.4	N/A	N/A	47.9	56.4	60.0%	131.1K	Closed weights	N/A	N/A	80.9%	80.7%	92.5%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
61	OPGPT-5.4-miniOpenAI	GPT-5.4 mini	56.5	84.9	N/A	N/A	18.5	60.0	60.0%	400K	Closed weights	$0.75	$4.5	88.0%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
62	MIMiniMax M1 80KMiniMax	MiniMax M1 80K	56.3	45.3	N/A	69.4	69.4	39.9	80.0%	1M	Closed weights	N/A	N/A	70.0%	81.1%	76.9%	N/A	65.0%	N/A	N/A	N/A	N/A	86.0%
63	XIMiMo V2 FlashXiaomi	MiMo-V2-Flash	55.9	72.8	36.8	34.4	56.1	81.6	100.0%	262.1K	Open weights	$0.14	$0.28	83.7%	84.9%	94.1%	N/A	N/A	N/A	N/A	N/A	58.3%	N/A
64	OPo3OpenAI	o3	55.8	72.0	24.6	25.0	90.5	65.1	100.0%	200K	Closed weights	$2	$8	83.3%	N/A	86.4%	N/A	N/A	N/A	N/A	N/A	49.7%	91.6%
65	ZAGLM 4.5 AirZhipu AI	GLM-4.5-Air	55.1	54.5	1.8	90.3	59.2	74.9	100.0%	131.1K	Open weights	N/A	N/A	75.0%	81.4%	N/A	N/A	70.7%	N/A	N/A	N/A	21.3%	89.4%
66	AMNova 2 LiteAmazon	Nova 2 Lite	55.1	62.3	N/A	N/A	36.8	67.5	60.0%	1M	Closed weights	$0.33	$2.75	79.6%	80.9%	91.0%	N/A	71.0%	N/A	N/A	N/A	N/A	N/A
67	OPo4 miniOpenAI	o4-mini	55.0	67.0	29.8	N/A	69.0	49.7	80.0%	200K	Closed weights	$1.1	$4.4	81.4%	N/A	92.7%	N/A	N/A	N/A	N/A	N/A	51.5%	93.4%
68	MIMiniMax M2.1MiniMax	MiniMax M2.1	54.8	65.5	43.9	N/A	49.1	59.4	80.0%	204.8K	Open weights	$0.30	$1.2	81.0%	88.0%	81.0%	N/A	78.0%	N/A	N/A	N/A	62.0%	N/A
69	MELlama 3.3 70BMeta	Llama 3.3 70B Instruct	54.6	25.0	N/A	68.6	66.9	68.7	80.0%	128K	Open weights	N/A	N/A	50.5%	68.9%	N/A	86.0%	N/A	77.0%	88.4%	92.1%	N/A	N/A
70	ACQwen3 Next 80B A3B ThinkingAlibaba Cloud / Qwen Team	Qwen3-Next-80B-A3B-Thinking	54.1	58.4	N/A	37.5	59.5	62.1	80.0%	131.1K	Open weights	$0.144	$1.43	77.2%	82.7%	87.8%	N/A	N/A	N/A	N/A	88.9%	N/A	N/A
71	ACQwen3.5 35B A3BAlibaba Cloud / Qwen Team	Qwen3.5-35B-A3B	53.3	48.3	62.3	43.8	57.1	57.0	100.0%	262.1K	Open weights	N/A	N/A	84.2%	85.3%	N/A	N/A	N/A	N/A	N/A	91.9%	61.0%	N/A
72	ACQwen2.5 72BAlibaba Cloud / Qwen Team	Qwen2.5 72B Instruct	53.1	22.6	N/A	80.1	60.3	58.1	80.0%	131.1K	Closed weights	$1.4	$5.6	49.0%	71.1%	N/A	N/A	55.5%	83.1%	86.6%	84.1%	N/A	N/A
73	GOGemini 2.0 FlashGoogle	Gemini 2.0 Flash	53.1	33.8	N/A	97.1	27.8	60.0	80.0%	1M	Closed weights	$0.10	$0.40	62.1%	76.4%	N/A	N/A	35.1%	89.7%	N/A	N/A	N/A	N/A
74	SASarvam 105BSarvam AI	Sarvam-105B	52.8	60.3	22.8	67.1	50.0	65.1	100.0%	131.1K	Open weights	N/A	N/A	78.7%	81.7%	96.7%	90.6%	N/A	N/A	N/A	84.8%	49.5%	N/A
75	MELongCat Flash ChatMeituan	LongCat-Flash-Chat	52.8	50.4	N/A	54.8	53.1	53.5	80.0%	128K	Closed weights	N/A	N/A	73.2%	82.7%	61.3%	89.7%	48.0%	N/A	88.4%	89.6%	N/A	N/A
76	GOGemini 2.0 Flash LiteGoogle	Gemini 2.0 Flash-Lite	52.6	26.7	N/A	86.0	N/A	51.4	60.0%	1M	Closed weights	$0.075	$0.30	51.5%	71.6%	N/A	N/A	N/A	86.8%	N/A	N/A	N/A	N/A
77	MELlama 3.1 70BMeta	Llama 3.1 70B Instruct	52.4	51.8	N/A	55.2	61.2	37.9	80.0%	128K	Closed weights	N/A	N/A	41.7%	66.4%	N/A	83.6%	N/A	N/A	80.5%	87.5%	N/A	N/A
78	ACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen Team	Qwen3 VL 32B Thinking	51.7	49.6	N/A	N/A	47.4	61.1	60.0%	N/A	Closed weights	N/A	N/A	73.1%	82.1%	83.7%	88.7%	N/A	N/A	N/A	87.8%	N/A	N/A
79	ACQwen2.5 VL 32BAlibaba Cloud / Qwen Team	Qwen2.5 VL 32B Instruct	51.5	19.4	N/A	75.7	82.2	32.0	80.0%	N/A	Closed weights	N/A	N/A	46.0%	68.8%	N/A	78.4%	N/A	82.2%	91.5%	N/A	N/A	N/A
80	MAKimi K2Moonshot AI	Kimi K2-Instruct-0905	51.4	55.4	N/A	46.6	54.0	47.9	80.0%	N/A	Closed weights	N/A	N/A	75.1%	81.1%	49.5%	89.5%	53.7%	N/A	N/A	89.8%	N/A	69.6%
81	OPGPT-4-TurboOpenAI	GPT-4 Turbo	51.1	21.6	N/A	70.2	55.4	69.2	80.0%	128K	Closed weights	$10	$30	48.0%	N/A	N/A	86.5%	N/A	72.6%	87.1%	N/A	N/A	N/A
82	INMercury 2Inception	Mercury 2	50.8	51.9	N/A	N/A	44.3	57.6	60.0%	128K	Closed weights	$0.25	$0.75	74.0%	N/A	91.1%	N/A	67.0%	N/A	N/A	N/A	N/A	N/A
83	MIPhi 4 Reasoning PlusMicrosoft	Phi 4 Reasoning Plus	50.3	42.9	N/A	N/A	66.3	41.5	60.0%	N/A	Closed weights	$0.125	$0.50	68.9%	76.0%	78.0%	N/A	53.1%	N/A	N/A	84.9%	N/A	81.3%
84	AMNova LiteAmazon	Nova Lite	49.2	46.7	N/A	63.1	34.2	54.6	80.0%	300K	Closed weights	$0.06	$0.24	42.0%	N/A	N/A	80.5%	N/A	73.3%	85.4%	89.7%	N/A	N/A
85	MAMistral Small 4Mistral AI	Mistral Small 4	49.1	47.4	N/A	N/A	61.1	36.1	60.0%	256K	Open weights	$0.15	$0.60	71.2%	78.0%	83.8%	N/A	63.6%	N/A	N/A	N/A	N/A	N/A
86	ACQwen3 235B A22BAlibaba Cloud / Qwen Team	Qwen3-235B-A22B-Instruct-2507	49.0	59.1	N/A	20.8	52.3	65.7	80.0%	262.1K	Open weights	N/A	N/A	77.5%	83.0%	70.3%	N/A	N/A	N/A	N/A	88.7%	N/A	N/A
87	GOGemini 1.5 ProGoogle	Gemini 1.5 Pro	48.6	31.5	N/A	58.8	41.5	72.9	80.0%	2.1M	Closed weights	N/A	N/A	59.1%	75.8%	N/A	85.9%	N/A	86.5%	84.1%	N/A	N/A	N/A
88	MELlama 4 MaverickMeta	Llama 4 Maverick	48.5	44.4	N/A	35.7	43.2	79.5	80.0%	1M	Closed weights	N/A	N/A	69.8%	80.5%	N/A	85.5%	43.4%	61.2%	N/A	N/A	N/A	N/A
89	MIMiniMax M1 40KMiniMax	MiniMax M1 40K	48.5	43.5	N/A	51.6	59.7	37.6	80.0%	N/A	Closed weights	N/A	N/A	69.2%	80.6%	74.6%	N/A	62.3%	N/A	N/A	N/A	N/A	83.3%
90	ACQwen3.6 35B A3BAlibaba Cloud / Qwen Team	Qwen3.6-35B-A3B	48.2	62.3	N/A	34.9	30.3	66.1	80.0%	262.1K	Open weights	N/A	N/A	86.0%	85.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
91	GOGemma 4 12BGoogle	Gemma 4 12B	48.1	60.8	N/A	N/A	29.3	52.2	60.0%	N/A	Closed weights	N/A	N/A	78.8%	77.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
92	MIPhi 4 ReasoningMicrosoft	Phi 4 Reasoning	47.9	37.7	N/A	N/A	73.6	30.5	60.0%	N/A	Closed weights	$0.125	$0.50	65.8%	74.3%	62.9%	N/A	53.8%	N/A	N/A	83.4%	N/A	75.3%
93	GOGemma 2 27BGoogle	Gemma 2 27B	47.1	45.5	94.1	25.6	8.6	67.0	100.0%	N/A	Closed weights	N/A	N/A	N/A	N/A	N/A	75.2%	N/A	42.3%	51.8%	N/A	N/A	N/A
94	SASarvam 30BSarvam AI	Sarvam-30B	47.0	39.2	8.8	45.7	77.8	71.8	100.0%	128K	Open weights	N/A	N/A	66.5%	80.0%	96.7%	85.1%	N/A	N/A	92.1%	N/A	35.5%	N/A
95	ACQwen2.5 Coder 32BAlibaba Cloud / Qwen Team	Qwen2.5-Coder 32B Instruct	45.4	39.4	N/A	39.3	68.0	33.5	80.0%	128K	Closed weights	$0.287	$0.861	N/A	50.4%	N/A	75.1%	31.4%	57.2%	92.7%	N/A	N/A	N/A
96	GOGemma 3 27BGoogle	Gemma 3 27B	45.1	15.3	N/A	89.0	39.2	44.3	80.0%	131.1K	Closed weights	N/A	N/A	42.4%	67.5%	N/A	N/A	29.7%	89.0%	87.8%	90.4%	N/A	N/A
97	NVNemotron 3 NanoNVIDIA	Nemotron 3 Nano (30B A3B)	45.1	54.5	N/A	N/A	18.3	65.2	60.0%	262.1K	Open weights	N/A	N/A	75.0%	78.3%	99.2%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
98	IBGranite 3.3 8BIBM	Granite 3.3 8B Instruct	45.0	N/A	N/A	13.4	80.8	39.6	60.0%	128K	Closed weights	N/A	N/A	N/A	N/A	N/A	65.5%	N/A	N/A	89.7%	74.8%	N/A	81.2%
99	MIMiniMax M2MiniMax	MiniMax M2	44.9	59.7	15.4	N/A	50.2	52.4	80.0%	196.6K	Open weights	$0.30	$1.2	78.0%	82.0%	78.0%	N/A	83.0%	N/A	N/A	N/A	44.0%	N/A
100	NVLlama 3.1 Nemotron Nano 8BNVIDIA	Llama 3.1 Nemotron Nano 8B V1	44.2	28.9	N/A	45.2	84.4	14.7	80.0%	N/A	Closed weights	N/A	N/A	54.1%	N/A	47.1%	N/A	N/A	N/A	N/A	79.3%	N/A	N/A
101	DEDeepSeek-R1DeepSeek	DeepSeek-R1-0528	44.1	65.5	0.0	25.0	55.8	77.2	100.0%	131.1K	Closed weights	N/A	N/A	81.0%	85.0%	87.5%	N/A	73.3%	N/A	N/A	N/A	8.9%	91.4%
102	ACQwen2.5 14BAlibaba Cloud / Qwen Team	Qwen2.5 14B Instruct	43.9	21.4	N/A	73.1	51.2	32.7	80.0%	N/A	Closed weights	$0.35	$1.4	45.5%	63.7%	N/A	79.7%	N/A	80.0%	83.5%	N/A	N/A	N/A
103	NVLlama 3.1 Nemotron 70BNVIDIA	Llama 3.1 Nemotron 70B Instruct	43.8	33.3	N/A	53.2	N/A	48.5	60.0%	128K	Open weights	N/A	N/A	N/A	N/A	N/A	80.2%	N/A	N/A	N/A	N/A	N/A	N/A
104	MAMistral Small 3.1 24BMistral AI	Mistral Small 3.1 24B Instruct	43.5	19.0	79.4	40.7	59.2	19.6	100.0%	N/A	Closed weights	N/A	N/A	46.0%	66.8%	N/A	80.6%	N/A	69.3%	88.4%	N/A	N/A	N/A
105	OPGPT-5.4-nanoOpenAI	GPT-5.4 nano	42.8	70.9	N/A	N/A	8.4	41.7	60.0%	400K	Closed weights	$0.20	$1.25	82.8%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
106	ACQwen3 VL 235B A22BAlibaba Cloud / Qwen Team	Qwen3 VL 235B A22B Instruct	42.7	N/A	N/A	25.0	44.7	63.7	60.0%	262.1K	Closed weights	N/A	N/A	N/A	81.8%	74.7%	88.8%	N/A	N/A	N/A	87.8%	N/A	N/A
107	MIPhi 3.5 MoEMicrosoft	Phi-3.5-MoE-instruct	42.4	41.3	N/A	34.3	39.7	58.4	80.0%	N/A	Closed weights	N/A	N/A	36.8%	45.3%	N/A	78.9%	N/A	59.5%	70.7%	N/A	N/A	N/A
108	ACQwen3 Next 80B A3BAlibaba Cloud / Qwen Team	Qwen3-Next-80B-A3B-Instruct	41.8	48.7	N/A	16.7	49.3	54.0	80.0%	131.1K	Open weights	$0.144	$0.574	72.9%	80.6%	69.5%	N/A	N/A	N/A	N/A	87.6%	N/A	N/A
109	OPGPT-4o-miniOpenAI	GPT-4o mini	41.5	12.1	N/A	52.5	56.9	55.3	80.0%	128K	Closed weights	$0.15	$0.60	40.2%	N/A	N/A	82.0%	N/A	70.2%	87.2%	N/A	N/A	N/A
110	ANClaude Haiku 3.5Anthropic	Claude 3.5 Haiku	41.2	13.8	N/A	56.8	62.3	38.0	80.0%	200K	Closed weights	N/A	N/A	41.6%	65.0%	N/A	N/A	N/A	69.4%	88.1%	N/A	N/A	N/A
111	ACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen Team	Qwen3 VL 30B A3B Thinking	40.3	53.4	N/A	33.3	32.1	38.8	80.0%	262.1K	Closed weights	N/A	N/A	74.4%	80.5%	83.1%	87.6%	N/A	N/A	N/A	81.7%	N/A	N/A
112	ACQwen3 MaxAlibaba Cloud / Qwen Team	Qwen3 Max	40.3	33.2	N/A	N/A	36.1	57.6	60.0%	262.1K	Closed weights	$0.861	$3.44	62.0%	N/A	81.6%	N/A	N/A	N/A	N/A	N/A	N/A	N/A
113	NRHermes 3 70BNous Research	Hermes 3 70B	40.2	29.8	N/A	34.0	N/A	65.8	60.0%	131.1K	Closed weights	N/A	N/A	66.1%	47.2%	N/A	79.1%	N/A	20.8%	N/A	N/A	N/A	N/A
114	ANClaude Sonnet 3Anthropic	Claude 3 Sonnet	40.0	48.8	N/A	38.7	20.0	53.6	80.0%	200K	Closed weights	N/A	N/A	40.4%	56.8%	N/A	79.0%	N/A	43.1%	73.0%	N/A	N/A	N/A
115	ACQwen3 30B A3BAlibaba Cloud / Qwen Team	Qwen3 30B A3B	39.7	37.7	N/A	N/A	49.2	30.4	60.0%	128K	Closed weights	N/A	N/A	65.8%	N/A	70.9%	N/A	62.6%	N/A	N/A	N/A	N/A	80.4%
116	GOGemma 3 12BGoogle	Gemma 3 12B	39.2	13.4	N/A	74.8	32.4	43.6	80.0%	131.1K	Closed weights	N/A	N/A	40.9%	60.6%	N/A	N/A	24.6%	83.8%	85.4%	88.9%	N/A	N/A
117	ALJamba 1.5 LargeAI21 Labs	Jamba 1.5 Large	38.3	46.1	N/A	31.9	N/A	33.9	60.0%	256K	Closed weights	N/A	N/A	36.9%	53.5%	N/A	81.2%	N/A	N/A	N/A	N/A	N/A	N/A
118	GODiffusionGemma 26B A4BGoogle	DiffusionGemma 26B-A4B	38.3	50.0	N/A	N/A	18.6	44.8	60.0%	N/A	Closed weights	N/A	N/A	73.2%	77.6%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
119	DEDeepSeek-V3DeepSeek	DeepSeek-V3 0324	38.1	42.2	N/A	32.3	36.1	41.9	80.0%	163.8K	Closed weights	N/A	N/A	68.4%	81.2%	N/A	N/A	49.2%	N/A	N/A	N/A	N/A	59.4%
120	ACQwen2 72BAlibaba Cloud / Qwen Team	Qwen2 72B Instruct	38.0	22.8	N/A	41.4	46.6	47.3	80.0%	N/A	Closed weights	N/A	N/A	42.4%	64.4%	N/A	82.3%	N/A	59.7%	86.0%	N/A	N/A	N/A
121	MIPhi 4Microsoft	Phi 4	36.9	29.7	N/A	56.1	38.5	21.3	80.0%	16K	Closed weights	$0.125	$0.50	56.1%	70.4%	N/A	84.8%	N/A	80.4%	82.6%	63.0%	N/A	N/A
122	GOGemini 1.5 FlashGoogle	Gemini 1.5 Flash	36.9	26.1	N/A	52.4	23.1	52.7	80.0%	1M	Closed weights	N/A	N/A	51.0%	67.3%	N/A	78.9%	N/A	77.9%	74.3%	N/A	N/A	N/A
123	AMNova MicroAmazon	Nova Micro	36.3	40.7	N/A	51.0	17.3	34.7	80.0%	128K	Closed weights	$0.035	$0.14	40.0%	N/A	N/A	77.6%	N/A	69.3%	81.1%	87.2%	N/A	N/A
124	ACQwen3.5 9BAlibaba Cloud / Qwen Team	Qwen3.5-9B	36.1	39.6	N/A	28.1	33.2	44.9	80.0%	262.1K	Open weights	N/A	N/A	81.7%	82.5%	N/A	N/A	N/A	N/A	N/A	91.5%	N/A	N/A
125	ACQwen3 VL 32BAlibaba Cloud / Qwen Team	Qwen3 VL 32B Instruct	36.0	42.9	N/A	N/A	27.0	36.6	60.0%	N/A	Closed weights	N/A	N/A	68.9%	78.6%	66.2%	86.4%	N/A	N/A	N/A	84.7%	N/A	N/A
126	DEDeepSeek-V3.1DeepSeek	DeepSeek-V3.1	36.0	53.9	15.1	3.1	48.2	61.6	100.0%	131.1K	Open weights	N/A	N/A	74.9%	83.7%	49.8%	N/A	56.4%	N/A	N/A	N/A	30.0%	66.3%
127	COCommand R+Cohere	Command R+	35.8	42.4	N/A	10.6	N/A	58.2	60.0%	128K	Closed weights	$0.15	$0.60	N/A	N/A	N/A	75.7%	N/A	N/A	N/A	N/A	N/A	N/A
128	MAMistral Small 3 24BMistral AI	Mistral Small 3 24B Instruct	34.3	18.1	N/A	48.6	43.8	29.3	80.0%	32K	Closed weights	N/A	N/A	45.3%	66.3%	N/A	N/A	N/A	70.6%	84.8%	82.9%	N/A	N/A
129	ANClaude Haiku 3Anthropic	Claude 3 Haiku	34.1	37.0	N/A	29.2	27.7	44.5	80.0%	200K	Closed weights	N/A	N/A	33.3%	N/A	N/A	75.2%	N/A	38.9%	75.9%	N/A	N/A	N/A
130	ACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen Team	Qwen3 VL 8B Thinking	32.9	44.8	N/A	29.2	14.4	42.5	80.0%	262.1K	Closed weights	N/A	N/A	69.9%	77.3%	80.3%	85.2%	N/A	N/A	N/A	83.2%	N/A	N/A
131	ACQwQ 32BAlibaba Cloud / Qwen Team	QwQ-32B	32.6	36.6	N/A	21.0	34.9	38.3	80.0%	N/A	Closed weights	$0.287	$0.861	65.2%	N/A	N/A	N/A	63.4%	N/A	N/A	83.9%	N/A	79.5%
132	ACQwen2.5 7BAlibaba Cloud / Qwen Team	Qwen2.5 7B Instruct	32.4	9.5	N/A	58.4	37.6	29.0	80.0%	131.1K	Closed weights	$0.175	$0.70	36.4%	56.3%	N/A	N/A	28.7%	75.5%	84.8%	71.2%	N/A	N/A
133	MELlama 4 ScoutMeta	Llama 4 Scout	32.3	30.2	N/A	22.9	23.8	60.0	80.0%	10M	Closed weights	N/A	N/A	57.2%	74.3%	N/A	79.6%	32.8%	50.3%	N/A	N/A	N/A	N/A
134	MIPhi 4 MiniMicrosoft	Phi 4 Mini	31.5	30.1	N/A	35.6	N/A	28.3	60.0%	128K	Open weights	$0.075	$0.30	25.2%	52.8%	N/A	67.3%	N/A	64.0%	N/A	N/A	N/A	N/A
135	GOGemini 2.5 Flash LiteGoogle	Gemini 2.5 Flash-Lite	30.7	35.3	N/A	N/A	12.8	46.9	60.0%	1M	Closed weights	$0.10	$0.40	64.6%	N/A	49.8%	N/A	33.7%	N/A	N/A	N/A	N/A	N/A
136	GOGemma 2 9BGoogle	Gemma 2 9B	30.2	27.3	58.8	18.4	2.3	49.5	100.0%	N/A	Closed weights	N/A	N/A	N/A	N/A	N/A	71.3%	N/A	36.6%	40.2%	N/A	N/A	N/A
137	MELlama 3.1 8BMeta	Llama 3.1 8B Instruct	29.5	29.3	N/A	20.7	49.2	15.2	80.0%	131.1K	Closed weights	N/A	N/A	30.4%	48.3%	N/A	69.4%	N/A	N/A	72.6%	80.4%	N/A	N/A
138	OPGPT-4OpenAI	GPT-4	28.5	8.6	N/A	36.3	10.8	74.9	80.0%	8.2K	Closed weights	$30	$60	35.7%	N/A	N/A	86.4%	N/A	42.0%	67.0%	N/A	N/A	N/A
139	OPGPT-4.1OpenAI	GPT-4.1	28.4	38.8	N/A	0.0	38.9	35.1	80.0%	1M	Closed weights	$2	$8	66.3%	N/A	46.4%	90.2%	N/A	N/A	N/A	87.4%	N/A	48.1%
140	ACQwen3.5 4BAlibaba Cloud / Qwen Team	Qwen3.5-4B	28.0	28.9	N/A	18.8	31.3	34.5	80.0%	N/A	Closed weights	N/A	N/A	76.2%	79.1%	N/A	N/A	N/A	N/A	N/A	89.8%	N/A	N/A
141	OPGPT-4oOpenAI	GPT-4o	27.9	45.7	N/A	N/A	10.3	21.6	60.0%	128K	Closed weights	N/A	N/A	70.1%	74.7%	N/A	85.7%	N/A	N/A	N/A	81.0%	N/A	13.1%
142	GOGemini DiffusionGoogle	Gemini Diffusion	27.2	12.7	N/A	N/A	48.4	23.2	60.0%	N/A	Closed weights	N/A	N/A	40.4%	N/A	23.3%	N/A	30.9%	N/A	89.6%	N/A	N/A	N/A
143	GOGemma 4 E4BGoogle	Gemma 4 E4B	26.8	30.6	N/A	N/A	18.2	31.8	60.0%	131.1K	Open weights	N/A	N/A	58.6%	69.4%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
144	MIPhi 3.5 miniMicrosoft	Phi-3.5-mini-instruct	25.9	32.4	N/A	24.4	18.7	26.9	80.0%	128K	Closed weights	N/A	N/A	30.4%	47.4%	N/A	69.0%	N/A	48.5%	62.8%	N/A	N/A	N/A
145	ACQwen3 VL 30B A3BAlibaba Cloud / Qwen Team	Qwen3 VL 30B A3B Instruct	25.0	46.1	N/A	8.3	10.8	30.9	80.0%	262.1K	Closed weights	N/A	N/A	70.4%	77.8%	69.3%	85.0%	N/A	N/A	N/A	85.8%	N/A	N/A
146	ACQwen2.5 Coder 7BAlibaba Cloud / Qwen Team	Qwen2.5-Coder 7B Instruct	24.4	12.1	N/A	19.9	50.5	16.0	80.0%	N/A	Closed weights	$0.144	$0.287	N/A	40.1%	N/A	67.6%	18.2%	46.6%	88.4%	N/A	N/A	N/A
147	ACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen Team	Qwen3 VL 4B Thinking	23.8	34.9	N/A	12.5	17.8	28.5	80.0%	262.1K	Closed weights	N/A	N/A	64.1%	73.6%	74.5%	81.5%	N/A	N/A	N/A	82.6%	N/A	N/A
148	MAMinistral 8BMistral AI	Ministral 8B Instruct	23.4	48.5	17.6	19.1	0.0	26.1	100.0%	131.1K	Open weights	N/A	N/A	N/A	N/A	N/A	65.0%	N/A	54.5%	34.8%	N/A	N/A	N/A
149	OPGPT-4.1-miniOpenAI	GPT-4.1 mini	22.5	35.8	N/A	6.3	18.3	27.9	80.0%	1M	Closed weights	$0.40	$1.6	65.0%	N/A	40.2%	87.5%	N/A	N/A	N/A	84.1%	N/A	49.6%
150	GOGemma 3n E4B LiteRTGoogle	Gemma 3n E4B Instructed LiteRT Preview	22.5	8.9	32.4	31.7	16.9	27.1	100.0%	N/A	Closed weights	N/A	N/A	23.7%	50.6%	11.6%	64.9%	13.2%	N/A	75.0%	N/A	N/A	N/A
151	GOGemma 3 4BGoogle	Gemma 3 4B	22.3	5.2	N/A	51.8	10.8	26.8	80.0%	131.1K	Closed weights	N/A	N/A	30.8%	43.6%	N/A	N/A	12.6%	75.6%	71.3%	90.2%	N/A	N/A
152	ALJamba 1.5 MiniAI21 Labs	Jamba 1.5 Mini	22.3	34.8	N/A	14.9	N/A	11.2	60.0%	256.1K	Closed weights	N/A	N/A	32.3%	42.5%	N/A	69.7%	N/A	N/A	N/A	N/A	N/A	N/A
153	IBIBM Granite 4.0 TinyIBM	IBM Granite 4.0 Tiny Preview	21.6	N/A	N/A	7.7	36.9	19.7	60.0%	N/A	Closed weights	N/A	N/A	N/A	N/A	N/A	60.4%	N/A	N/A	82.4%	63.0%	N/A	N/A
154	ACQwen2.5 Omni 7BAlibaba Cloud / Qwen Team	Qwen2.5-Omni-7B	20.7	5.2	N/A	44.3	26.1	7.8	80.0%	N/A	Closed weights	$0.10	$0.40	30.8%	47.0%	N/A	N/A	N/A	71.5%	78.7%	N/A	N/A	N/A
155	MELlama 3.2 3BMeta	Llama 3.2 3B Instruct	20.4	29.1	N/A	16.7	N/A	10.7	60.0%	128K	Closed weights	N/A	N/A	32.8%	N/A	N/A	63.4%	N/A	48.0%	N/A	77.4%	N/A	N/A
156	XAGrok 1.5xAI	Grok-1.5	19.3	9.1	N/A	34.5	21.5	13.3	80.0%	N/A	Closed weights	N/A	N/A	35.9%	51.0%	N/A	81.3%	N/A	50.6%	74.1%	N/A	N/A	N/A
157	GOGemma 3n E4BGoogle	Gemma 3n E4B Instructed	17.9	1.1	N/A	37.5	16.9	21.0	80.0%	32K	Closed weights	N/A	N/A	23.7%	50.6%	11.6%	64.9%	13.2%	N/A	75.0%	N/A	N/A	N/A
158	ACQwen3.5 2BAlibaba Cloud / Qwen Team	Qwen3.5-2B	16.8	27.2	N/A	N/A	7.7	11.6	60.0%	N/A	Closed weights	N/A	N/A	51.6%	66.5%	N/A	N/A	N/A	N/A	N/A	78.6%	N/A	N/A
159	MAPixtral 12BMistral AI	Pixtral-12B	15.2	N/A	N/A	18.6	16.9	8.3	60.0%	128K	Open weights	$0.15	$0.15	N/A	N/A	N/A	69.2%	N/A	48.1%	72.0%	61.3%	N/A	N/A
160	ACQwen2 7BAlibaba Cloud / Qwen Team	Qwen2 7B Instruct	15.1	3.0	N/A	22.4	17.1	23.1	80.0%	N/A	Closed weights	N/A	N/A	25.3%	44.1%	N/A	70.5%	26.6%	49.6%	79.9%	N/A	N/A	N/A
161	GOGemma 4 E2BGoogle	Gemma 4 E2B	14.3	15.9	N/A	N/A	8.0	19.9	60.0%	131.1K	Open weights	N/A	N/A	43.4%	60.0%	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
162	ACQwen3 VL 8BAlibaba Cloud / Qwen Team	Qwen3 VL 8B Instruct	12.6	N/A	N/A	4.2	8.9	28.9	60.0%	262.1K	Closed weights	N/A	N/A	N/A	71.6%	45.9%	80.7%	N/A	N/A	N/A	83.7%	N/A	N/A
163	OPGPT-3.5-TurboOpenAI	GPT-3.5 Turbo	12.5	5.2	N/A	20.9	12.3	13.6	80.0%	16.4K	Closed weights	$0.50	$1.5	30.8%	N/A	N/A	69.8%	N/A	43.1%	68.0%	N/A	N/A	N/A
164	OPGPT-4.1-nanoOpenAI	GPT-4.1 nano	11.4	24.1	N/A	N/A	0.0	5.3	60.0%	1M	Closed weights	$0.10	$0.40	50.3%	N/A	N/A	80.1%	N/A	N/A	N/A	74.5%	N/A	29.4%
165	GOGemma 3n E2B LiteRTGoogle	Gemma 3n E2B Instructed LiteRT (Preview)	8.3	4.8	8.8	12.3	7.0	10.1	100.0%	N/A	Closed weights	N/A	N/A	24.8%	40.5%	6.7%	60.1%	13.2%	N/A	66.5%	N/A	N/A	N/A
166	BAERNIE 4.5Baidu	ERNIE 4.5	8.1	26.0	N/A	0.0	0.0	0.1	80.0%	128K	Closed weights	N/A	N/A	74.0%	16.0%	N/A	41.9%	N/A	12.4%	N/A	N/A	N/A	N/A
167	ACQwen3 VL 4BAlibaba Cloud / Qwen Team	Qwen3 VL 4B Instruct	7.7	N/A	N/A	0.0	3.7	23.4	60.0%	262.1K	Closed weights	N/A	N/A	N/A	67.1%	46.6%	77.2%	N/A	N/A	N/A	82.3%	N/A	N/A
168	GOGemma 3n E2BGoogle	Gemma 3n E2B Instructed	6.9	1.9	N/A	12.5	7.0	7.8	80.0%	N/A	Closed weights	N/A	N/A	24.8%	40.5%	6.7%	60.1%	13.2%	N/A	66.5%	N/A	N/A	N/A
169	GOGemma 3 1BGoogle	Gemma 3 1B	2.7	0.4	N/A	6.9	1.0	3.2	80.0%	N/A	Closed weights	N/A	N/A	19.2%	14.7%	N/A	N/A	1.9%	48.0%	41.5%	80.2%	N/A	N/A
170	ACQwen3.5 0.8BAlibaba Cloud / Qwen Team	Qwen3.5-0.8B	0.3	0.0	N/A	N/A	0.0	1.3	60.0%	N/A	Closed weights	N/A	N/A	11.9%	42.3%	N/A	N/A	N/A	N/A	N/A	44.0%	N/A	N/A

Main price columns show official vendor API PAYG rates. Third-party offers remain on the dedicated pricing and model detail pages; unavailable official prices display as N/A.

Top overallGPT-5.6-Sol96.5 LLMBoard score Top open-weight modelKimi K2.6Rank #7 Lowest official input priceNova Micro$0.04 / 1M tokens Largest context windowLlama 4 Scout10M tokens Strongest reasoningGPT-5.6-Sol99.8 category score Strongest codingGPT-597.7 category score Most recent scored releaseGPT-5.6-Sol2026-07-09 Broadest evidenceQwen3.5 397B A17B100% category coverage

Common questions about llmboard.ai rankings.

What is the highest-ranked model right now?

GPT-5.6-Sol is currently ranked first with a published LLMBoard score of 96.5.

How are models ranked?

Each unique model appears once using its latest version with a published capability score. Source-native benchmark results are normalized within their own evaluation families; Arena and price signals remain separate.

How many models are tracked?

The current public catalog contains 297 published model products, including 170 with a current LLMBoard score.

Why do some prices show N/A?

N/A means the vendor's official API does not publish a valid standard PAYG price in the current registry. Third-party offers are tracked separately and never substituted into the official price columns.

How often is this page updated?

The page reads the current public API on each request. Benchmark and price dates still reflect when their underlying source records were last published.