Model intelligence

291 AI models

Capability (Epoch Capabilities Index and individual benchmarks from Epoch AI), API list prices and context windows (OpenRouter), release dates and open-weight status. Benchmarks are shown individually - never merged into one invented score.

Leads on ECI

GPT-6 Astra

ECI 166.6Epoch AI

Leads on GPQA Diamond

GPT-6 Astra

95.8%Epoch AI

Leads on SWE-bench Verified

Claude Opus 4.7

83.5%Epoch AI

Cheapest in ECI top 10

GPT-5.6 Sol

$2.00/M inputOpenRouter

Longest context

Grok 4.20 Multi-Agent

2M tokensOpenRouter

Best open-weight on ECI

Kimi K3

ECI 157.68Epoch AI

Epoch Capabilities Index by release date

Capability frontier

About ECI ↗

Source: Epoch AI (CC BY 4.0). ECI is Epoch's item-response model over many benchmarks; each model page shows its 90% confidence interval.

Blended $/1M tokens (3:1 input:output) vs ECI

Price vs capability

Only models with both an ECI score and an OpenRouter price. Normalisation: 75% input + 25% output price. Click a point to open the model.

291 models

2 filters:

#	Model	ECI ↑	AA idx	GPQA◆	SWE-v	FrontierMath	AIME	HLE	Terminal	Context	In $/M	Out $/M	Weights	Released
1	DeepSeek Coder 1.3B DeepSeek	62.2	—	—	—	—	—	—	—	—	—	—	Open source	2 Nov 2023
2	Cerebras-GPT-13B Cerebras	82.4	—	—	—	—	—	—	—	—	—	—	Open source	20 Mar 2023
3	StarCoder 2 3B Hugging Face	88.0	—	—	—	—	—	—	—	—	—	—	Open source	22 Feb 2024
4	DeepSeek Coder 6.7B DeepSeek	88.9	—	—	—	—	—	—	—	—	—	—	Open source	2 Nov 2023
5	Dolly 2.0-12b Databricks	88.9	—	—	—	—	—	—	—	—	—	—	Open source	11 Apr 2023
6	Baichuan1-7B Baichuan	89.8	—	—	—	—	—	—	—	—	—	—	Open source	1 Jun 2023
7	Phi-1.5 Microsoft	90.8	—	—	—	—	—	—	—	—	—	—	Open source	11 Sep 2023
8	XGen-7B Salesforce	92.8	—	—	—	—	—	—	—	—	—	—	Open source	27 Jun 2023
9	StarCoder 2 7B Hugging Face	92.9	—	—	—	—	—	—	—	—	—	—	Open source	20 Feb 2024
10	Gemma 2B Google	93.6	—	—	—	—	—	—	—	—	—	—	Open source	21 Feb 2024
11	MPT-7B MosaicML	94.0	—	—	—	—	—	—	—	—	—	—	Open source	5 May 2023
12	Falcon-7B Technology Innovation Institute	94.5	—	—	—	—	—	—	—	—	—	—	Open source	24 Apr 2023
13	DeepSeek Coder 33B DeepSeek	95.7	—	—	—	—	—	—	—	—	—	—	Open source	2 Nov 2023
14	Baichuan 2-7B Baichuan	95.8	—	—	—	—	—	—	—	—	—	—	Open source	20 Sep 2023
15	LLaMA-7B Meta	96.1	—	—	—	—	—	—	—	—	—	—	Open source	24 Feb 2023
16	Llama 2-7B Meta	98.5	—	—	—	—	—	—	—	—	—	—	Open source	18 Jul 2023
17	LLaMA-13B Meta	100.1	—	—	—	—	—	—	—	—	—	—	Open source	24 Feb 2023
18	MPT-30B MosaicML	100.2	—	—	—	—	—	—	—	—	—	—	Open source	22 Jun 2023
19	Llama 3.2 1B Meta	102.0	—	23.9	—	—	0.6	—	—	—	—	—	Open source	24 Sep 2024
20	Qwen2.5-Coder (1.5B) Alibaba (Qwen)	102.6	—	—	—	—	—	—	—	—	—	—	Open source	18 Sep 2024
21	Baichuan2-13B Baichuan	102.8	—	—	—	—	—	—	—	—	—	—	Open source	6 Sep 2023
22	Falcon-40B Technology Innovation Institute	104.0	—	—	—	—	—	—	—	—	—	—	Open source	25 May 2023
23	Yi 6B 01.AI	104.4	—	—	—	—	—	—	—	—	—	—	Open source	22 Nov 2023
24	StarCoder 2 15B Hugging Face	104.6	—	—	—	—	—	—	—	—	—	—	Open source	20 Feb 2024
25	Llama 2-13B Meta	105.8	—	—	—	—	—	—	—	—	—	—	Open source	18 Jul 2023
26	Qwen-7B Alibaba (Qwen)	106.5	—	—	—	—	—	—	—	—	—	—	Open source	28 Sep 2023
27	LLaMA-33B Meta	107.1	—	—	—	—	—	—	—	—	—	—	Open source	24 Feb 2023
28	Phi-2 Microsoft	107.6	—	—	—	—	—	—	—	—	—	—	Open source	12 Dec 2023
29	Mistral 7B v0.3 Mistral AI	108.7	—	15.2	—	—	0.3	—	—	—	—	—	Open source	27 May 2024
30	Falcon 2 11B Technology Innovation Institute	109.3	—	—	—	—	—	—	—	—	—	—	Open source	9 May 2024
31	LLaMA-65B Meta	109.9	—	—	—	—	—	—	—	—	—	—	Open source	24 Feb 2023
32	DeepSeek LLM 67B DeepSeek	110.5	—	24.6	—	—	0.8	—	—	—	—	—	Open source	29 Nov 2023
33	Gemma 7B Google	111.7	—	—	—	—	—	—	—	—	—	—	Open source	21 Feb 2024
34	Falcon-180B Technology Innovation Institute	111.9	—	—	—	—	—	—	—	—	—	—	Open source	6 Sep 2023
35	Mistral 7B v0.1 Mistral AI	112.0	—	—	—	—	—	—	—	—	—	—	Open source	27 Sep 2023
36	Qwen-14B Alibaba (Qwen)	112.8	—	—	—	—	—	—	—	—	—	—	Open source	24 Sep 2023
37	Qwen2.5-Coder (7B) Alibaba (Qwen)	112.9	—	—	—	—	—	—	—	—	—	—	Open source	18 Sep 2024
38	Llama 2-70B Meta	113.6	—	26.3	—	—	0.0	—	—	—	—	—	Open source	18 Jul 2023
39	Gemma 3 4B Google	116.0	—	23.2	—	—	7.5	—	—	131K	$0.050	$0.10	Open source	12 Mar 2025
40	Llama 3-8B Meta	116.3	—	26.1	—	—	1.9	—	—	—	—	—	Open source	18 Apr 2024
41	Llama 3.1-8B Meta	116.5	—	27.0	—	—	1.7	—	—	—	—	—	Open source	23 Jul 2024
42	Stable Beluga 2 Stability AI	117.0	—	—	—	—	—	—	—	—	—	—	Open source	20 Jul 2023
43	phi-3-mini 3.8B Microsoft	117.2	—	—	—	—	—	—	—	—	—	—	Open source	23 Apr 2024
44	Yi-34B 01.AI	117.3	—	14.7	—	—	—	—	—	—	—	—	Open source	2 Nov 2023
45	Mixtral 8x7B Mistral AI	118.4	—	30.6	—	—	—	—	—	—	—	—	Open source	11 Dec 2023
46	Qwen2.5-7B Alibaba (Qwen)	118.4	—	35.5	—	—	2.5	—	—	—	—	—	Open source	19 Sep 2024
47	Mistral Nemo Mistral AI	118.6	—	29.9	—	—	—	—	—	131K	$0.019	$0.030	Open source	18 Jul 2024
48	Command R+ Cohere	119.3	—	—	—	—	—	—	—	—	—	—	Open source	30 Aug 2024
49	Qwen2.5-Coder-32B Alibaba (Qwen)	119.4	—	—	—	—	—	—	—	—	—	—	Open source	18 Sep 2024
50	Gemma 2 9B Google	119.8	—	27.5	—	—	0.6	—	—	—	—	—	Open source	24 Jun 2024
51	phi-3-medium 14B Microsoft	121.2	—	27.6	—	—	—	—	—	—	—	—	Open source	23 Apr 2024
52	phi-3-small 7.4B Microsoft	121.8	—	—	—	—	—	—	—	—	—	—	Open source	23 Apr 2024
53	Mixtral 8x22B Mistral AI	122.0	—	34.1	—	—	—	—	—	—	—	—	Open source	17 Apr 2024
54	Gemma 2 27B Google	122.1	—	36.5	—	—	1.4	—	—	8K	$0.65	$0.65	Open source	24 Jun 2024
55	Llama 3-70B Meta	122.9	—	40.6	—	—	4.3	—	—	—	—	—	Open source	18 Apr 2024
56	Gemma 3 12B Google	123.5	3.8	39.5	—	—	16.7	—	—	131K	$0.050	$0.15	Open source	12 Mar 2025
57	DeepSeek-V2 (MoE-236B, May 2024) DeepSeek	124.8	—	—	—	—	—	—	—	—	—	—	Open source	7 May 2024
58	Qwen2-72B Alibaba (Qwen)	125.3	—	40.8	—	—	—	—	—	—	—	—	Open source	7 Jun 2024
59	Llama 3.2 90B Meta	125.5	—	41.0	—	—	2.6	—	—	—	—	—	Open source	24 Sep 2024
60	Llama 3.1-70B Meta	125.9	—	44.2	—	—	3.6	—	—	—	—	—	Open source	23 Jul 2024
61	Mistral Small 3 Mistral AI	127.1	—	47.3	—	—	6.7	—	—	33K	$0.050	$0.080	Open source	30 Jan 2025
62	Llama 3.3 70B Meta	127.3	—	47.4	—	—	5.1	—	—	—	—	—	Open source	6 Dec 2024
63	Mistral Small 3.1 Mistral AI	127.5	—	47.5	—	—	5.8	—	—	—	—	—	Open source	17 Mar 2025
64	Mistral Large 2 (Jul 2024) Mistral AI	127.5	—	49.0	—	—	8.5	—	—	—	—	—	Open source	24 Jul 2024
65	Mistral Large 2 (Nov 2024) Mistral AI	128.5	—	51.3	—	—	7.8	—	—	—	—	—	Open source	18 Nov 2024
66	Qwen2.5-32B Alibaba (Qwen)	128.5	—	46.1	—	—	7.4	—	—	—	—	—	Open source	17 Sep 2024
67	Llama 3.1-405B Meta	128.8	—	50.9	—	—	9.7	—	—	—	—	—	Open source	23 Jul 2024
68	Qwen2.5-72B Alibaba (Qwen)	129.0	—	49.1	—	—	8.1	—	—	—	—	—	Open source	19 Sep 2024
69	Llama 4 Scout Meta	129.6	—	51.8	—	—	7.8	—	—	1.31M	$0.10	$0.30	Open source	5 Apr 2025
70	Gemma 3 27B Google	130.0	4.9	47.7	—	—	22.5	—	—	131K	$0.080	$0.45	Open source	12 Mar 2025
71	Phi 4 Microsoft	130.4	—	56.1	—	—	13.8	—	—	16K	$0.070	$0.14	Open source	12 Dec 2024
72	Magistral Small 1.2 Mistral AI	131.4	—	47.6	—	—	28.1	—	—	—	—	—	Open source	18 Sep 2025
73	Mistral Small 3.2 Mistral AI	131.7	—	49.1	—	—	30.3	—	—	—	—	—	Open source	20 Jun 2025
74	Llama 4 Maverick Meta	132.2	—	—	—	—	—	5.7	—	1.05M	$0.19	$0.65	Open source	6 Apr 2025
75	DeepSeek V3 DeepSeek	132.4	—	56.5	—	—	15.8	—	—	164K	$0.26	$1.03	Open source	26 Dec 2024
76	Magistral Small 1.0 Mistral AI	133.2	—	56.1	—	—	30.0	—	—	—	—	—	Open source	10 Jun 2025
77	DeepSeek-R1-Distill-Qwen-14B DeepSeek	135.4	—	44.7	—	—	50.6	—	—	—	—	—	Open source	20 Jan 2025
78	DeepSeek-V3 (Mar 2025) DeepSeek	135.9	—	67.6	—	—	37.8	—	—	—	—	—	Open source	24 Mar 2025
79	Qwen3 8B Alibaba (Qwen)· reasoning	136.2	—	56.8	—	—	56.1	—	—	131K	$0.12	$0.46	Open source	28 Apr 2025
80	Qwen3 30B A3B Alibaba (Qwen)· reasoning	136.2	—	61.7	—	—	62.8	—	—	131K	$0.13	$0.52	Open source	29 Apr 2025
81	Qwen3-30B-A3B-Instruct (Jul 2025) Alibaba (Qwen)	137.4	—	55.6	—	—	62.2	—	—	—	—	—	Open source	29 Jul 2025
82	DeepSeek-R1-Distill-Qwen-32B DeepSeek	137.4	—	64.1	—	—	55.6	—	—	—	—	—	Open source	20 Jan 2025
83	QwQ-32B Alibaba (Qwen)	137.6	—	65.3	—	—	59.2	—	—	—	—	—	Open source	5 Mar 2025
84	gpt-oss-20b OpenAI· reasoning	137.8	9.0	60.8	—	—	65.3	—	3.4	131K	$0.018	$0.090	Open source	5 Aug 2025
85	Qwen3 14B Alibaba (Qwen)· reasoning	138.2	—	63.8	—	—	66.4	—	—	131K	$0.12	$0.24	Open source	29 Apr 2025
86	Qwen3 32B Alibaba (Qwen)· reasoning	138.5	—	65.7	—	—	66.9	—	—	131K	$0.080	$0.28	Open source	29 Apr 2025
87	Qwen3-235B-A22B-Instruct (Jul 2025) Alibaba (Qwen)	138.9	—	—	—	—	—	—	—	—	—	—	Open source	25 Jul 2025
88	R1 DeepSeek· reasoning	139.0	11.4	71.7	—	—	53.3	—	—	64K	$0.70	$2.50	Open source	20 Jan 2025
89	Qwen3 235B A22B Alibaba (Qwen)· reasoning	139.4	—	70.7	—	—	—	—	—	131K	$0.46	$1.82	Open source	28 Apr 2025
90	Qwen3.5-9B Alibaba (Qwen)· reasoning	139.4	11.2	79.0	—	—	61.7	—	9.2	262K	$0.10	$0.15	Open source	24 Feb 2026
91	Qwen3-30B-A3B-Thinking (Jul 2025) Alibaba (Qwen)	139.6	—	70.1	—	—	70.3	—	—	—	—	—	Open source	30 Jul 2025
92	DeepSeek V3.1 DeepSeek· reasoning	139.9	—	—	—	—	—	—	—	164K	$0.25	$0.95	Open source	21 Aug 2025
93	gpt-oss-120b OpenAI· reasoning	139.9	11.6	75.8	—	—	88.9	—	18.7	131K	$0.037	$0.17	Open source	5 Aug 2025
94	Kimi K2 (Jul 2025) Moonshot AI	140.1	—	—	—	—	—	—	—	—	—	—	Open source	12 Jul 2025
95	DeepSeek-R1 (May 2025) DeepSeek	141.3	—	76.3	—	—	66.4	—	—	—	—	—	Open source	28 May 2025
96	Mistral Medium 3.5 Mistral AI· reasoning	141.4	14.2	—	—	—	—	—	—	262K	$1.50	$7.50	Open source	28 Apr 2026
97	Gemma 4 26B A4B Google· reasoning	141.8	—	73.2	—	—	82.2	—	—	262K	$0.090	$0.30	Open source	2 Apr 2026
98	Qwen3.5-35B-A3B Alibaba (Qwen)· reasoning	142.5	—	83.5	—	—	70.0	—	—	262K	$0.16	$1.30	Open source	24 Feb 2026
99	Gemma 4 31B Google· reasoning	142.7	—	75.8	—	—	73.3	—	—	262K	$0.090	$0.34	Open source	2 Apr 2026
100	GLM 4.7 Z.ai (Zhipu AI)· reasoning	143.5	—	83.3	—	—	83.3	—	33.4	205K	$0.60	$2.20	Open source	22 Dec 2025

Showing 100 of 291. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Next →Export CSV