Skip to content
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

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
201Qwen3 VL 32B Instruct—131K$0.1023 Oct 2025
202Granite 4.0 Micro—131K$0.01720 Oct 2025
203Qwen3 VL 8B Thinking
Alibaba (Qwen)· reasoning
—131K$0.1814 Oct 2025
204Qwen3 VL 8B Instruct—262K$0.1214 Oct 2025
205Qwen3 VL 30B A3B Thinking
Alibaba (Qwen)· reasoning
—262K$0.206 Oct 2025
206Qwen3 VL 30B A3B Instruct—262K$0.156 Oct 2025
207GLM 4.6
Z.ai (Zhipu AI)· reasoning
—205K$0.4330 Sep 2025
208GLM-4.6 (Together)———30 Sep 2025
209Cydonia 24B V4.1—131K$0.3027 Sep 2025
210Qwen3 VL 235B A22B Thinking
Alibaba (Qwen)· reasoning
—131K$0.4023 Sep 2025
211Qwen3 VL 235B A22B Instruct—262K$0.2123 Sep 2025
212Qwen3 Next 80B A3B Thinking
Alibaba (Qwen)· reasoning
—262K$0.1511 Sep 2025
213Qwen3 Next 80B A3B Instruct—262K$0.1011 Sep 2025
214Kimi K2 0905 (Novita)———5 Sep 2025
215Kimi K2 Instruct (0905)———5 Sep 2025
216Kimi K2 (Sep 2025)———5 Sep 2025
217Kimi K2 0905—262K$0.604 Sep 2025
218Hermes 4 405B
Nous Research· reasoning
—131K$1.0026 Aug 2025
219GLM 4.5V
Z.ai (Zhipu AI)· reasoning
—66K$0.6011 Aug 2025
220GLM-4.5 Thinking———5 Aug 2025
221Qwen3 Coder 30B A3B Instruct—262K$0.07031 Jul 2025
222Qwen3 30B A3B Instruct 2507—262K$0.04829 Jul 2025
223GLM 4.5
Z.ai (Zhipu AI)· reasoning
—131K$0.6025 Jul 2025
224GLM 4.5 Air
Z.ai (Zhipu AI)· reasoning
—131K$0.1325 Jul 2025
225Qwen3 Coder 480B A35B—262K$0.3023 Jul 2025
226UI-TARS 7B —128K$0.1022 Jul 2025
227Qwen3 235B A22B Instruct 2507—262K$0.08721 Jul 2025
228Kimi K2 Instruct———12 Jul 2025
229Kimi K2 0711—131K$0.5711 Jul 2025
230Uncensored—128K$0.209 Jul 2025
231Hunyuan A13B Instruct
Tencent· reasoning
—131K$0.148 Jul 2025
232ERNIE 4.5 VL 424B A47B
Baidu· reasoning
—123K$0.4230 Jun 2025
233Mistral Small 3.2 24B—256K$0.09420 Jun 2025
234MiniMax-M1-80k———13 Jun 2025
235R1 0528
DeepSeek· reasoning
—164K$0.5028 May 2025
236Llama Guard 4 12B—164K$0.1830 Apr 2025
237Qwen3-4B———29 Apr 2025
238Qwen3-1.7B———29 Apr 2025
239Llama 4 Maverick (FP8)———5 Apr 2025
240Mistral Small 3.1 24B—128K$0.3517 Mar 2025
241Cohere Command A———13 Mar 2025
242Reka Flash 3
Reka AI· reasoning
—66K$0.1012 Mar 2025
243Gemma 3 1B———12 Mar 2025
244Skyfall 36B V2—33K$0.5510 Mar 2025
245Qwen2.5 VL 72B Instruct—128K$0.801 Feb 2025
246DeepSeek-R1-Distill-Qwen-1.5B———20 Jan 2025
247DeepSeek-R1-Distill-Llama-70B———20 Jan 2025
248MiniMax-01—1M$0.2015 Jan 2025
249Codestral———13 Jan 2025
250Eurus-2-7B-PRIME
Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Shanghai AI Lab,Peking University,Shanghai Jiao Tong University,CUHK Shenzhen Research Institute
———31 Dec 2024
251Llama 3.3 Euryale 70B—131K$0.6518 Dec 2024
252Llama 3.3 70B Instruct—131K$0.106 Dec 2024
253Tulu 3 (Tülu 3) 70B———21 Nov 2024
254Qwen2.5 Coder 32B Instruct—33K$0.6611 Nov 2024
255UnslopNemo 12B—1.02M$0.408 Nov 2024
256Magnum v4 72B—33K$2.5022 Oct 2024
257Qwen2.5 7B Instruct—33K$0.1016 Oct 2024
258Ministral 8B———16 Oct 2024
259Llama 3.2 1B Instruct—60K$0.02725 Sep 2024
260Llama 3.2 3B Instruct—131K$0.05025 Sep 2024
261Llama 3.2 11B———24 Sep 2024
262Llama 3.2 3B———24 Sep 2024
263Qwen2.5 72B Instruct—33K$0.3619 Sep 2024
264Qwen2.5-14B———19 Sep 2024
265Pixtral 12B———17 Sep 2024
266Mistral Small v24.09———17 Sep 2024
267DeepSeek-V2.5 (Sep 2024)———6 Sep 2024
268Llama 3.1 Euryale 70B v2.2—131K$0.8528 Aug 2024
269Hermes 3 70B Instruct—131K$0.7018 Aug 2024
270Phi-3.5-MoE———17 Aug 2024
271Hermes 3 405B Instruct—131K$1.0016 Aug 2024
272Phi-3.5-mini———16 Aug 2024
273Llama 3 8B Lunaris—8K$0.04013 Aug 2024
274Llama 3.1 8B Instruct—131K$0.05023 Jul 2024
275Llama 3.1 70B Instruct—131K$0.4023 Jul 2024
276Hermes 2 Theta Llama-3 70B———20 Jun 2024
277DeepSeek-Coder-V2 236B———17 Jun 2024
278Yi-1.5-34B
01.AI
———13 May 2024
279Mixtral 8x22B Instruct—66K$2.0017 Apr 2024
280WizardLM-2 8x22B—66K$0.6216 Apr 2024
281Qwen1.5-32B———3 Apr 2024
282DBRX
Databricks
———27 Mar 2024
283Qwen1.5-72B———4 Feb 2024
284Qwen1.5-7B———4 Feb 2024
285Qwen1.5-14B———4 Feb 2024
286Mistral 7B v0.2———11 Dec 2023
287ReMM SLERP 13B—6K$0.3522 Jul 2023
288Baichuan 1-13B
Baichuan
———11 Jul 2023
289MythoMax 13B—8K$0.0802 Jul 2023
290Vicuna-13B-v1.3
Large Model Systems Organization,University of California (UC) Berkeley
———18 Jun 2023
291BLIP-2 (Q-Former)
Salesforce Research
———6 Feb 2023
Showing 91 of 291. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.← PrevExport CSV