Skip to content
Model intelligence

676 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

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.

#ModelECI ↑ContextIn $/MReleased
1stablelm-tuned-alpha-7b
54.3——19 Apr 2023
2DeepSeek Coder 1.3B62.2——2 Nov 2023
3Cerebras-GPT-13B82.4——20 Mar 2023
4Qwen2.5-Coder-0.5B
87.4——18 Sep 2024
5StarCoder 2 3B88.0——22 Feb 2024
6DeepSeek Coder 6.7B88.9——2 Nov 2023
7Dolly 2.0-12b
Databricks
88.9——11 Apr 2023
8RedPajama-INCITE-7B-Base
89.7——4 May 2023
9Baichuan1-7B
Baichuan
89.8——1 Jun 2023
10Phi-1.590.8——11 Sep 2023
11open_llama_7b
91.0——7 Jun 2023
12Qwen-1_8B
92.3——30 Nov 2023
13XGen-7B
Salesforce
92.8——27 Jun 2023
14StarCoder 2 7B92.9——20 Feb 2024
15Gemma 2B93.6——21 Feb 2024
16MPT-7B
MosaicML
94.0——5 May 2023
17vicuna-13b-v1.1
94.0——12 Apr 2023
18CodeQwen1.5-7B
94.2——15 Apr 2024
19Falcon-7B94.5——24 Apr 2023
20DeepSeek Coder 33B95.7——2 Nov 2023
21Baichuan 2-7B
Baichuan
95.8——20 Sep 2023
22LLaMA-7B96.1——24 Feb 2023
23chatglm2-6b
98.4——24 Jun 2023
24Llama 2-7B98.5——18 Jul 2023
25LLaMA-13B100.1——24 Feb 2023
26MPT-30B
MosaicML
100.2——22 Jun 2023
27INTELLECT-1
Prime Intellect,Hugging Face,Arcee AI
100.4——29 Nov 2024
28Llama 3.2 1B102.0——24 Sep 2024
29internlm-7b
102.4——5 Jul 2023
30Qwen2.5-Coder (1.5B)102.6——18 Sep 2024
31Baichuan2-13B
Baichuan
102.8——6 Sep 2023
32Falcon-40B104.0——25 May 2023
33Yi 6B
01.AI
104.4——22 Nov 2023
34StarCoder 2 15B104.6——20 Feb 2024
35Llama 2-34B104.8——18 Jul 2023
36PaLM 2-S
105.8——17 May 2023
37Llama 2-13B105.8——18 Jul 2023
38Qwen-7B106.5——28 Sep 2023
39LLaMA-33B107.1——24 Feb 2023
40Yi-9B
107.3——1 Mar 2024
41Nemotron-4 15B107.4——26 Feb 2024
42Qwen2.5-Coder-3B
107.4——18 Sep 2024
43Phi-2107.6——12 Dec 2023
44PaLM 2-M
108.0——17 May 2023
45DeepSeek-Coder-V2-Lite-Base
108.6——13 Jun 2024
46Mistral 7B v0.3108.7——27 May 2024
47Falcon 2 11B109.3——9 May 2024
48LLaMA-65B109.9——24 Feb 2023
49DeepSeek LLM 67B110.5——29 Nov 2023
50Gemma 7B111.7——21 Feb 2024
51internlm-20b
111.8——18 Sep 2023
52Falcon-180B111.9——6 Sep 2023
53Mistral 7B v0.1112.0——27 Sep 2023
54Qwen-14B112.8——24 Sep 2023
55Qwen2.5-Coder (7B)112.9——18 Sep 2024
56GPT-3.5 Turbo (Jun 2023)113.1——13 Jun 2023
57Llama 2-70B113.6——18 Jul 2023
58PaLM 2-L
114.8——17 May 2023
59GPT-3.5 Turbo (Jan 2024)115.6——25 Jan 2024
60Gemma 3 4B116.0131K$0.05012 Mar 2025
61Qwen2.5-Coder-14B
116.3——18 Sep 2024
62Llama 3-8B116.3——18 Apr 2024
63Llama 3.1-8B116.5——23 Jul 2024
64Gemini 1.0 Pro117.0——13 Dec 2023
65Stable Beluga 2117.0——20 Jul 2023
66phi-3-mini 3.8B117.2——23 Apr 2024
67Yi-34B
01.AI
117.3——2 Nov 2023
68Ministral 3B118.1——16 Oct 2024
69Claude 3 Haiku118.3——7 Mar 2024
70Mixtral 8x7B118.4——11 Dec 2023
71Qwen2.5-7B118.4——19 Sep 2024
72GPT-3.5 Turbo (Nov 2023)118.5——6 Nov 2023
73Mistral Nemo118.6131K$0.01918 Jul 2024
74Claude 2.1119.2——21 Nov 2023
75Command R+119.3——30 Aug 2024
76Qwen2.5-Coder-32B119.4——18 Sep 2024
77Gemma 2 9B119.8——24 Jun 2024
78Claude 2120.1——11 Jul 2023
79Claude Instant120.2——9 Aug 2023
80Claude 3 Sonnet120.7——29 Feb 2024
81phi-3-medium 14B121.2——23 Apr 2024
82phi-3-small 7.4B121.8——23 Apr 2024
83Mixtral 8x22B122.0——17 Apr 2024
84Mistral Large122.0128K$2.0026 Feb 2024
85Gemma 2 27B122.18K$0.6524 Jun 2024
86Gemini 1.5 Flash (May 2024)122.6——23 May 2024
87Llama 3-70B122.9——18 Apr 2024
88GPT-4 (Jun 2023)123.1——13 Jun 2023
89Gemma 3 12B123.5131K$0.05012 Mar 2025
90Amazon Nova Pro123.8——3 Dec 2024
91DeepSeek-V2 (MoE-236B, May 2024)124.8——7 May 2024
92Qwen2-72B125.3——7 Jun 2024
93Llama 3.2 90B125.5——24 Sep 2024
94GPT-4 (Mar 2023)125.9——14 Mar 2023
95Llama 3.1-70B125.9——23 Jul 2024
96GPT-4 Turbo (Nov 2023)126.5——25 Jan 2024
97GPT-4o-mini126.6128K$0.1518 Jul 2024
98Gemini 1.5 Pro (May 2024)126.9——14 May 2024
99Claude 3 Opus126.9——29 Feb 2024
100Mistral Small 3127.133K$0.05030 Jan 2025
Showing 100 of 676. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Next →Export CSV