Skip to content
Model intelligence

236 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
Claude Opus 5.5
ECI 167.35Epoch 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
Claude Sonnet 5.5
$2.00/M inputOpenRouter
Longest context
Grok 4.20 Multi-Agent
2M tokensOpenRouter
Best open-weight on ECI
Kimi K3
ECI 157.61Epoch 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
101GPT-4o (Aug 2024)128.8——6 Aug 2024
102GPT-4 Turbo (Apr 2024)127.3——9 Apr 2024
103Claude 3.5 Haiku127.2——22 Oct 2024
104Gemini 1.5 Pro (May 2024)126.9——14 May 2024
105Claude 3 Opus126.9——29 Feb 2024
106GPT-4o-mini126.6128K$0.1518 Jul 2024
107GPT-4 Turbo (Nov 2023)126.5——25 Jan 2024
108GPT-4 (Mar 2023)125.9——14 Mar 2023
109Amazon Nova Pro123.8——3 Dec 2024
110GPT-4 (Jun 2023)123.1——13 Jun 2023
111Gemini 1.5 Flash (May 2024)122.6——23 May 2024
112Mistral Large122.0128K$2.0026 Feb 2024
113Claude 3 Sonnet120.7——29 Feb 2024
114Claude Instant120.3——9 Aug 2023
115Claude 2120.1——11 Jul 2023
116Claude 2.1119.3——21 Nov 2023
117GPT-3.5 Turbo (Nov 2023)118.6——6 Nov 2023
118Claude 3 Haiku118.4——7 Mar 2024
119Ministral 3B118.1——16 Oct 2024
120Gemini 1.0 Pro117.0——13 Dec 2023
121Qwen2.5-Coder-14B
116.4——18 Sep 2024
122GPT-3.5 Turbo (Jan 2024)115.7——25 Jan 2024
123PaLM 2-L
115.0——17 May 2023
124GPT-3.5 Turbo (Jun 2023)113.4——13 Jun 2023
125internlm-20b
112.1——18 Sep 2023
126DeepSeek-Coder-V2-Lite-Base
108.9——13 Jun 2024
127PaLM 2-M
108.3——17 May 2023
128Qwen2.5-Coder-3B
107.8——18 Sep 2024
129Nemotron-4 15B107.7——26 Feb 2024
130Yi-9B
107.6——1 Mar 2024
131PaLM 2-S
106.2——17 May 2023
132Llama 2-34B105.2——18 Jul 2023
133internlm-7b
102.9——5 Jul 2023
134INTELLECT-1
Prime Intellect,Hugging Face,Arcee AI
100.9——29 Nov 2024
135chatglm2-6b
99.0——24 Jun 2023
136CodeQwen1.5-7B
94.9——15 Apr 2024
137vicuna-13b-v1.1
94.7——12 Apr 2023
138Qwen-1_8B
93.0——30 Nov 2023
139open_llama_7b
91.7——7 Jun 2023
140RedPajama-INCITE-7B-Base
90.5——4 May 2023
141Qwen2.5-Coder-0.5B
88.2——18 Sep 2024
142stablelm-tuned-alpha-7b
55.8——19 Apr 2023
143GPT-6.1 Sol (unknown thinking)———29 Sep 2026
144GPT-6.1 Sol (medium)———29 Sep 2026
145GPT-6 Sol (xhigh)———22 Sep 2026
146GPT-6 Sol (medium)———22 Sep 2026
147GPT-6 Luna (xhigh)———22 Sep 2026
148GPT-6 Sol (low)———22 Sep 2026
149GPT-6 Luna (medium)———22 Sep 2026
150GPT-6 Luna (low)———22 Sep 2026
151GPT-6 Sol (none)———22 Sep 2026
152GPT-6 Luna (none)———22 Sep 2026
153GPT-6 Sol (unknown thinking)———22 Sep 2026
154GPT-6 Luna (unknown thinking)———22 Sep 2026
155Grok 4.7 (unknown)———21 Sep 2026
156Grok 4.7 (xhigh)———21 Sep 2026
157SWE-2 (max)———10 Sep 2026
158Mercury 2.5 (unknown)———8 Sep 2026
159GPT-6 Astra (pro, max)———3 Sep 2026
160GLM-5.3 (unknown thinking)———14 Aug 2026
161Qwen3.8 Max (xhigh)———2 Aug 2026
162Qwen3.8 Max (unknown)———2 Aug 2026
163Gemini 3.5 Flash-Lite (medium)———21 Jul 2026
164GPT-5.6 Sol (pro, max)———9 Jul 2026
165GPT-5.6 Sol (pro, xhigh)———9 Jul 2026
166GPT-5.6 Sol (pro, unknown thinking)———9 Jul 2026
167Composer 2.5———18 May 2026
168AI co-mathematician———8 May 2026
169Claude Mythos Preview (Early)———7 Apr 2026
170SWE-1.6———7 Apr 2026
171Qwen 3.6 Plus (2026-04-02)———31 Mar 2026
172GPT-5.4 mini (xhigh)———17 Mar 2026
173GPT-5.4 mini (none)———17 Mar 2026
174GPT-5.4 nano (no thinking)———17 Mar 2026
175GPT-5.4 nano (low)———17 Mar 2026
176GPT-5.4 mini (low)———17 Mar 2026
177GPT-5.4 mini (medium)———17 Mar 2026
178GPT-5.4 nano (medium)———17 Mar 2026
179GPT-5.4 nano (xhigh)———17 Mar 2026
180GPT-5.4 mini (unknown thinking)———17 Mar 2026
181GPT-5.4 Pro (web)———5 Mar 2026
182Gemini 3 Deep Think———12 Feb 2026
183GPT-5.3 Codex (xhigh)———5 Feb 2026
184GPT-5.2 Pro (web)———11 Dec 2025
185Grok 4.1 Fast———19 Nov 2025
186Gemini 3 Pro Preview———18 Nov 2025
187Grok 4.1———17 Nov 2025
188Gemini 2.5 Flash-Lite (Sep 2025)———25 Sep 2025
189Qwen3-Max-Instruct———24 Sep 2025
190GPT-5-codex———15 Sep 2025
191GPT-5 mini (minimal)———7 Aug 2025
192GPT-5 nano (low)———7 Aug 2025
193GPT-5 nano (minimal)———7 Aug 2025
194GPT-5 mini (medium)———7 Aug 2025
195GPT-5 nano (medium)———7 Aug 2025
196GPT-5 mini (low)———7 Aug 2025
197GPT-5 mini (unknown thinking)———7 Aug 2025
198GPT-5 nano (unknown thinking)———7 Aug 2025
199Gemini 2.5 Deep Think———1 Aug 2025
200Grok 4 Heavy (web app)———10 Jul 2025
Showing 100 of 236. Benchmark cells are % (best reported setting). 3.9K benchmark results in total.← PrevNext →Export CSV