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
201Mixtral 8x7B118.5——11 Dec 2023
202Claude 3 Haiku118.4——7 Mar 2024
203Ministral 3B118.1——16 Oct 2024
204Yi-34B
01.AI
117.4——2 Nov 2023
205phi-3-mini 3.8B117.4——23 Apr 2024
206Stable Beluga 2117.1——20 Jul 2023
207Gemini 1.0 Pro117.0——13 Dec 2023
208Llama 3.1-8B116.6——23 Jul 2024
209Llama 3-8B116.5——18 Apr 2024
210Qwen2.5-Coder-14B
116.4——18 Sep 2024
211Gemma 3 4B116.0131K$0.05012 Mar 2025
212GPT-3.5 Turbo (Jan 2024)115.7——25 Jan 2024
213PaLM 2-L
115.0——17 May 2023
214Llama 2-70B113.8——18 Jul 2023
215GPT-3.5 Turbo (Jun 2023)113.4——13 Jun 2023
216Qwen2.5-Coder (7B)113.2——18 Sep 2024
217Qwen-14B113.0——24 Sep 2023
218Mistral 7B v0.1112.2——27 Sep 2023
219Falcon-180B112.2——6 Sep 2023
220internlm-20b
112.1——18 Sep 2023
221Gemma 7B112.0——21 Feb 2024
222DeepSeek LLM 67B110.6——29 Nov 2023
223LLaMA-65B110.2——24 Feb 2023
224Falcon 2 11B109.6——9 May 2024
225Mistral 7B v0.3109.0——27 May 2024
226DeepSeek-Coder-V2-Lite-Base
108.9——13 Jun 2024
227PaLM 2-M
108.3——17 May 2023
228Phi-2108.0——12 Dec 2023
229Qwen2.5-Coder-3B
107.8——18 Sep 2024
230Nemotron-4 15B107.7——26 Feb 2024
231Yi-9B
107.6——1 Mar 2024
232LLaMA-33B107.4——24 Feb 2023
233Qwen-7B106.8——28 Sep 2023
234PaLM 2-S
106.2——17 May 2023
235Llama 2-13B106.2——18 Jul 2023
236Llama 2-34B105.2——18 Jul 2023
237StarCoder 2 15B105.0——20 Feb 2024
238Yi 6B
01.AI
104.8——22 Nov 2023
239Falcon-40B104.5——25 May 2023
240Baichuan2-13B
Baichuan
103.2——6 Sep 2023
241Qwen2.5-Coder (1.5B)103.0——18 Sep 2024
242internlm-7b
102.9——5 Jul 2023
243Llama 3.2 1B102.0——24 Sep 2024
244INTELLECT-1
Prime Intellect,Hugging Face,Arcee AI
100.9——29 Nov 2024
245MPT-30B
MosaicML
100.7——22 Jun 2023
246LLaMA-13B100.6——24 Feb 2023
247Llama 2-7B99.1——18 Jul 2023
248chatglm2-6b
99.0——24 Jun 2023
249LLaMA-7B96.7——24 Feb 2023
250Baichuan 2-7B
Baichuan
96.4——20 Sep 2023
251DeepSeek Coder 33B96.3——2 Nov 2023
252Falcon-7B95.1——24 Apr 2023
253CodeQwen1.5-7B
94.9——15 Apr 2024
254vicuna-13b-v1.1
94.7——12 Apr 2023
255MPT-7B
MosaicML
94.6——5 May 2023
256Gemma 2B94.2——21 Feb 2024
257StarCoder 2 7B93.6——20 Feb 2024
258XGen-7B
Salesforce
93.4——27 Jun 2023
259Qwen-1_8B
93.0——30 Nov 2023
260open_llama_7b
91.7——7 Jun 2023
261Phi-1.591.6——11 Sep 2023
262Baichuan1-7B
Baichuan
90.5——1 Jun 2023
263RedPajama-INCITE-7B-Base
90.5——4 May 2023
264Dolly 2.0-12b
Databricks
89.7——11 Apr 2023
265DeepSeek Coder 6.7B89.7——2 Nov 2023
266StarCoder 2 3B88.8——22 Feb 2024
267Qwen2.5-Coder-0.5B
88.2——18 Sep 2024
268Cerebras-GPT-13B83.3——20 Mar 2023
269DeepSeek Coder 1.3B63.7——2 Nov 2023
270stablelm-tuned-alpha-7b
55.8——19 Apr 2023
271GPT-6.1 Sol
OpenAI· reasoning
—1.05M$2.0029 Sep 2026
272GPT-6 Sol
OpenAI· reasoning
—1.05M$2.0022 Sep 2026
273Grok 4.7
xAI· reasoning
—500K$2.0021 Sep 2026
274MiMo-V2.6-Pro
Xiaomi· reasoning
—1.05M$0.4321 Sep 2026
275Qwen3.8 2.4T A95B
Alibaba (Qwen)· reasoning
—1.05M$2.0012 Aug 2026
276MiMo-V2.6-Flash
Xiaomi· reasoning
—1.05M$0.1421 Sep 2026
277GPT-6 Luna
OpenAI· reasoning
—1.05M$0.1022 Sep 2026
278Qwen3.8 27B
Alibaba (Qwen)· reasoning
—1M$0.4214 Aug 2026
279Gemini 3.1 Pro Preview
Google· reasoning
—1.05M$2.0019 Feb 2026
280MiMo-V2.5-Pro
Xiaomi· reasoning
—1.05M$0.4322 Apr 2026
281Hy3 preview
Tencent· reasoning
—262K$0.1822 Apr 2026
282Grok 4.3
xAI· reasoning
—1M$1.2530 Apr 2026
283Ling 3.0 Flash VL—262K$0.02110 Sep 2026
284Ling 3.0 Flash Fin—262K$0.06027 Aug 2026
285Ling 3.0 Flash—262K$0.02123 Jul 2026
286LongCat 2.0
Meituan· reasoning
—1.05M$0.3020 Jul 2026
287Qwen3.6 35B A3B
Alibaba (Qwen)· reasoning
—262K$0.1527 Apr 2026
288Gemini 2.5 Pro
Google· reasoning
—1.05M$1.2517 Jun 2025
289Gemini 3.1 Flash Lite Preview
Google· reasoning
—1.05M$0.253 Mar 2026
290Qwen3.5-122B-A10B
Alibaba (Qwen)· reasoning
—262K$0.2625 Feb 2026
291DeepSeek V3.1 Terminus
DeepSeek· reasoning
—164K$0.3022 Sep 2025
292Command A—256K$2.5013 Mar 2025
293Nemotron 3.5 Lightning
NVIDIA· reasoning
—262K$0.06011 Aug 2026
294Nemotron 3 Super
NVIDIA· reasoning
—262K$0.08011 Mar 2026
295Qwen3 235B A22B Thinking 2507
Alibaba (Qwen)· reasoning
—131K$0.2325 Jul 2025
296Mercury 2.5
Inception Labs· reasoning
—260K$0.0408 Sep 2026
297Mistral Small 4
Mistral AI· reasoning
—262K$0.1516 Mar 2026
298Granite 4.2 8B
IBM· reasoning
—131K$0.06031 Aug 2026
299o3 Mini High
OpenAI· reasoning
—200K$1.1012 Feb 2025
300Trinity Large Thinking
Arcee AI· reasoning
—262K$0.251 Apr 2026
Showing 100 of 678. Benchmark cells are % (best reported setting). 3.9K benchmark results in total.← PrevNext →Export CSV