Skip to content
Model intelligence

678 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
101Qwen3 Max
Alibaba (Qwen)· reasoning
142.4262K$0.7824 Sep 2025
102o1
OpenAI· reasoning
141.9200K$15.017 Dec 2024
103Gemma 4 26B A4B
Google· reasoning
141.8262K$0.0762 Apr 2026
104Claude Sonnet 4
Anthropic· reasoning
141.7200K$3.0022 May 2025
105Gemini 2.5 Flash (May 2025)141.5——20 May 2025
106Mistral Medium 3.5
Mistral AI· reasoning
141.4262K$1.5028 Apr 2026
107DeepSeek-R1 (May 2025)141.3——28 May 2025
108Claude 3.7 Sonnet141.2——24 Feb 2025
109Gemini 2.5 Flash (Jun 2025)140.8——17 Jun 2025
110Grok-3 mini140.3——24 Jun 2025
111o3 Mini
OpenAI· reasoning
140.3200K$1.1031 Jan 2025
112Kimi K2 (Jul 2025)140.1——12 Jul 2025
113Gemini 2.5 Flash (Apr 2025)140.0——17 Apr 2025
114gpt-oss-120b
OpenAI· reasoning
139.9131K$0.0375 Aug 2025
115DeepSeek V3.1
DeepSeek· reasoning
139.9164K$0.2521 Aug 2025
116Qwen3-30B-A3B-Thinking (Jul 2025)139.6——30 Jul 2025
117Qwen3.5-9B
Alibaba (Qwen)· reasoning
139.5262K$0.1024 Feb 2026
118GPT-5 Nano
OpenAI· reasoning
139.4400K$0.0507 Aug 2025
119Qwen3 235B A22B
Alibaba (Qwen)· reasoning
139.3131K$0.4628 Apr 2025
120R1
DeepSeek· reasoning
139.064K$0.7020 Jan 2025
121Qwen3-235B-A22B-Instruct (Jul 2025)138.9——25 Jul 2025
122Qwen3 32B
Alibaba (Qwen)· reasoning
138.5131K$0.08029 Apr 2025
123Grok 3138.3——9 Apr 2025
124Qwen3 14B
Alibaba (Qwen)· reasoning
138.2131K$0.1229 Apr 2025
125gpt-oss-20b
OpenAI· reasoning
137.8131K$0.0185 Aug 2025
126QwQ-32B137.6——5 Mar 2025
127DeepSeek-R1-Distill-Qwen-32B137.4——20 Jan 2025
128Qwen3-30B-A3B-Instruct (Jul 2025)137.4——29 Jul 2025
129GPT-4.1136.81.05M$2.0014 Apr 2025
130GPT-4.5136.7——27 Feb 2025
131Qwen3 30B A3B
Alibaba (Qwen)· reasoning
136.2131K$0.1229 Apr 2025
132Qwen3 8B
Alibaba (Qwen)· reasoning
136.2131K$0.1228 Apr 2025
133DeepSeek-V3 (Mar 2025)135.9——24 Mar 2025
134o1-mini135.8——12 Sep 2024
135DeepSeek-R1-Distill-Qwen-14B135.4——20 Jan 2025
136Gemini 2.0 Flash Thinking (Jan 2025)135.4——21 Jan 2025
137Gemini 2.0 Pro135.1——5 Feb 2025
138GPT-4.1 Mini135.01.05M$0.4014 Apr 2025
139o1-preview134.8——12 Sep 2024
140Gemini 2.0 Flash (Feb 2025)134.7——5 Feb 2025
141Gemini 2.0 Flash (Dec 2024)134.7——11 Dec 2024
142Mistral Medium 3134.1131K$0.407 May 2025
143Gemini 2.5 Flash-Lite (Jun 2025)133.9——17 Jun 2025
144Claude 3.5 Sonnet (October 2024)133.5——22 Oct 2024
145Magistral Small 1.0133.2——10 Jun 2025
146Qwen2.5-Max132.5——25 Jan 2025
147DeepSeek V3132.3164K$0.2626 Dec 2024
148Llama 4 Maverick132.21.05M$0.196 Apr 2025
149Mistral Small 3.2131.7——20 Jun 2025
150Gemini 1.5 Pro (Sept 2024)131.7——24 Sep 2024
151Magistral Small 1.2131.4——18 Sep 2025
152Grok-2 (Dec 2024)130.5——12 Dec 2024
153Phi 4130.416K$0.07012 Dec 2024
154Gemma 3 27B130.0131K$0.08012 Mar 2025
155Claude 3.5 Sonnet130.0——20 Jun 2024
156Llama 4 Scout129.71.31M$0.105 Apr 2025
157GPT-4.1 Nano129.61.05M$0.1014 Apr 2025
158Gemini 1.5 Flash (Sep 2024)129.4——24 Sep 2024
159Qwen2.5-72B129.0——19 Sep 2024
160GPT-4o (May 2024)129.0——13 May 2024
161GPT-4o (Nov 2024)128.8——20 Nov 2024
162GPT-4o (Aug 2024)128.8——6 Aug 2024
163Llama 3.1-405B128.8——23 Jul 2024
164Mistral Large 2 (Nov 2024)128.5——18 Nov 2024
165Qwen2.5-32B128.5——17 Sep 2024
166Mistral Large 2 (Jul 2024)127.5——24 Jul 2024
167Mistral Small 3.1127.5——17 Mar 2025
168Llama 3.3 70B127.3——6 Dec 2024
169GPT-4 Turbo (Apr 2024)127.3——9 Apr 2024
170Claude 3.5 Haiku127.2——22 Oct 2024
171Mistral Small 3127.133K$0.05030 Jan 2025
172Gemini 1.5 Pro (May 2024)126.9——14 May 2024
173Claude 3 Opus126.9——29 Feb 2024
174GPT-4o-mini126.6128K$0.1518 Jul 2024
175GPT-4 Turbo (Nov 2023)126.5——25 Jan 2024
176Llama 3.1-70B125.9——23 Jul 2024
177GPT-4 (Mar 2023)125.9——14 Mar 2023
178Llama 3.2 90B125.5——24 Sep 2024
179Qwen2-72B125.3——7 Jun 2024
180DeepSeek-V2 (MoE-236B, May 2024)124.8——7 May 2024
181Amazon Nova Pro123.8——3 Dec 2024
182Gemma 3 12B123.5131K$0.05012 Mar 2025
183GPT-4 (Jun 2023)123.1——13 Jun 2023
184Llama 3-70B122.9——18 Apr 2024
185Gemini 1.5 Flash (May 2024)122.6——23 May 2024
186Gemma 2 27B122.18K$0.6524 Jun 2024
187Mixtral 8x22B122.0——17 Apr 2024
188Mistral Large122.0128K$2.0026 Feb 2024
189phi-3-small 7.4B121.8——23 Apr 2024
190phi-3-medium 14B121.2——23 Apr 2024
191Claude 3 Sonnet120.7——29 Feb 2024
192Claude Instant120.3——9 Aug 2023
193Claude 2120.1——11 Jul 2023
194Gemma 2 9B119.8——24 Jun 2024
195Qwen2.5-Coder-32B119.5——18 Sep 2024
196Command R+119.3——30 Aug 2024
197Claude 2.1119.3——21 Nov 2023
198Mistral Nemo118.7131K$0.01918 Jul 2024
199GPT-3.5 Turbo (Nov 2023)118.6——6 Nov 2023
200Qwen2.5-7B118.5——19 Sep 2024
Showing 100 of 678. Benchmark cells are % (best reported setting). 3.9K benchmark results in total.← PrevNext →Export CSV