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
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
501GPT-5 mini (medium)———7 Aug 2025
502GPT-5 nano (medium)———7 Aug 2025
503GPT-5 mini (low)———7 Aug 2025
504GPT-5 mini (unknown thinking)———7 Aug 2025
505GPT-5 nano (unknown thinking)———7 Aug 2025
506qwen3-4b-instruct-2507
———6 Aug 2025
507GLM-4.5 Thinking———5 Aug 2025
508Codestral 2508—256K$0.301 Aug 2025
509Gemini 2.5 Deep Think———1 Aug 2025
510Qwen3 Coder 30B A3B Instruct—262K$0.07031 Jul 2025
511Qwen3 30B A3B Instruct 2507—262K$0.04829 Jul 2025
512chutes/GLM-4.5-FP8
———27 Jul 2025
513GLM 4.5
Z.ai (Zhipu AI)· reasoning
—131K$0.6025 Jul 2025
514GLM 4.5 Air
Z.ai (Zhipu AI)· reasoning
—131K$0.1325 Jul 2025
515Qwen3 Coder 480B A35B—262K$0.3023 Jul 2025
516UI-TARS 7B —128K$0.1022 Jul 2025
517Gemini 2.5 Flash Lite
Google· reasoning
—1.05M$0.1022 Jul 2025
518Qwen3 235B A22B Instruct 2507—262K$0.08721 Jul 2025
519Kimi K2 Instruct———12 Jul 2025
520Kimi K2 0711—131K$0.5711 Jul 2025
521Grok 4 Heavy (web app)———10 Jul 2025
522Uncensored—128K$0.209 Jul 2025
523Hunyuan A13B Instruct
Tencent· reasoning
—131K$0.148 Jul 2025
524Morph V3 Fast—82K$0.807 Jul 2025
525Morph V3 Large—262K$0.907 Jul 2025
526ERNIE 4.5 VL 424B A47B
Baidu· reasoning
—123K$0.4230 Jun 2025
527Mistral Small 3.2 24B—256K$0.09420 Jun 2025
528MiniMax M1
MiniMax· reasoning
—1M$0.4017 Jun 2025
529Gemini 2.5 Flash
Google· reasoning
—1.05M$0.3017 Jun 2025
530gemini-2.5-flash-lite-preview-06-17 (Default thinking length)———17 Jun 2025
531MiniMax-M1-80k———13 Jun 2025
532Magistral Medium 1.1———10 Jun 2025
533Gemini 2.5 Pro Preview 06-05
Google· reasoning
—1.05M$1.255 Jun 2025
534Gemini 2.5 Pro Preview (Jun 2025)———5 Jun 2025
535R1 0528
DeepSeek· reasoning
—164K$0.5028 May 2025
536deepseek-r1-0528-qwen3-8b
———28 May 2025
537codex-mini-2025-05-16
———16 May 2025
538Llama Guard 4 12B—164K$0.1830 Apr 2025
539Qwen3-4B———29 Apr 2025
540Qwen3-1.7B———29 Apr 2025
541Qwen Plus (Apr 2025)———28 Apr 2025
542Gemini 2.5 Flash Preview (Apr 2025)———17 Apr 2025
543o4 Mini High
OpenAI· reasoning
—200K$1.1016 Apr 2025
544o4-mini (medium)———16 Apr 2025
545o4-mini (low)———16 Apr 2025
546QWQ-Plus———8 Apr 2025
547Llama 4 Maverick (FP8)———5 Apr 2025
548Gemini 2.5 Pro Preview (Mar 2025)———31 Mar 2025
549GPT-4o (Mar 2025)———27 Mar 2025
550Gemini 2.5 Pro Exp (Mar 2025)———25 Mar 2025
551o1-pro
OpenAI· reasoning
—200K$150.019 Mar 2025
552o1 Pro (low)———19 Mar 2025
553Mistral Small 3.1 24B—128K$0.3517 Mar 2025
554Cohere Command A———13 Mar 2025
555Reka Flash 3
Reka AI· reasoning
—66K$0.1012 Mar 2025
556Gemma 3 1B———12 Mar 2025
557computer-use-preview-2025-03-11
———11 Mar 2025
558Skyfall 36B V2—33K$0.5510 Mar 2025
559Sonar Pro—200K$3.007 Mar 2025
560Sonar Reasoning Pro
Perplexity· reasoning
—128K$2.007 Mar 2025
561Sonar Deep Research
Perplexity· reasoning
—128K$2.007 Mar 2025
562GPT-4.5 Preview (Feb 2025)———27 Feb 2025
563Saba—33K$0.2017 Feb 2025
564Gemini 2.0 Pro Exp (Feb 2025)———5 Feb 2025
565Gemini 2.0 Flash-Lite———5 Feb 2025
566Aion-RP 1.0 (8B)—33K$0.804 Feb 2025
567Qwen-Plus—1M$0.261 Feb 2025
568Qwen2.5 VL 72B Instruct—128K$0.801 Feb 2025
569o3-mini (medium)———31 Jan 2025
570GPT-4o (Jan 2025)———29 Jan 2025
571Sonar—127K$1.0027 Jan 2025
572Qwen Plus (Jan 2025)———25 Jan 2025
573Gemini 2.0 Flash Thinking Exp———21 Jan 2025
574DeepSeek-R1-Distill-Qwen-1.5B———20 Jan 2025
575DeepSeek-R1-Distill-Llama-70B———20 Jan 2025
576MiniMax-01—1M$0.2015 Jan 2025
577Codestral———13 Jan 2025
578Eurus-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
579Llama 3.3 Euryale 70B—131K$0.6518 Dec 2024
580Command R7B (12-2024)—128K$0.03714 Dec 2024
581Llama 3.3 70B Instruct—131K$0.106 Dec 2024
582Nova Pro 1.0—300K$0.805 Dec 2024
583Nova Lite 1.0—300K$0.0605 Dec 2024
584Nova Micro 1.0—128K$0.0355 Dec 2024
585Amazon Nova Lite———3 Dec 2024
586Amazon Nova Micro———3 Dec 2024
587Yi-Lightning
01.AI
———2 Dec 2024
588Tulu 3 (Tülu 3) 70B———21 Nov 2024
589GPT-4o (2024-11-20)—128K$2.5020 Nov 2024
590Mistral Large 2407—131K$2.0019 Nov 2024
591Qwen2.5 Coder 32B Instruct—33K$0.6611 Nov 2024
592UnslopNemo 12B—1.02M$0.408 Nov 2024
593Qwen2.5-Coder-3B-Instruct
———6 Nov 2024
594Qwen2.5-Coder-14B-Instruct
———6 Nov 2024
595Qwen-Turbo———1 Nov 2024
596Magnum v4 72B—33K$2.5022 Oct 2024
597Claude 3.5 Haiku (Oct 2024)———22 Oct 2024
598Claude 3.5 Sonnet (Oct 2024)———22 Oct 2024
599Qwen2.5 7B Instruct—33K$0.1016 Oct 2024
600Ministral 8B———16 Oct 2024
Showing 100 of 678. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.← PrevNext →Export CSV