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
601Gemini 1.5 Flash 8B———3 Oct 2024
602Llama 3.2 1B Instruct—60K$0.02725 Sep 2024
603Llama 3.2 3B Instruct—131K$0.05025 Sep 2024
604Llama 3.2 11B———24 Sep 2024
605Llama 3.2 3B———24 Sep 2024
606Qwen2.5 72B Instruct—33K$0.3619 Sep 2024
607Qwen2.5-14B———19 Sep 2024
608Pixtral 12B———17 Sep 2024
609Mistral Small v24.09———17 Sep 2024
610DeepSeek-V2.5 (Sep 2024)———6 Sep 2024
611Command R (08-2024)—128K$0.1530 Aug 2024
612c4ai-command-r-08-2024
———30 Aug 2024
613Qwen2-VL-72B-Instruct
———29 Aug 2024
614Qwen2-VL-7B-Instruct
———29 Aug 2024
615Llama 3.1 Euryale 70B v2.2—131K$0.8528 Aug 2024
616Hermes 3 70B Instruct—131K$0.7018 Aug 2024
617Phi-3.5-MoE———17 Aug 2024
618Hermes 3 405B Instruct—131K$1.0016 Aug 2024
619Phi-3.5-mini———16 Aug 2024
620Phi-3.5-vision-instruct
———16 Aug 2024
621InternVL-Chat-ViT-6B-Vicuna-13B
———16 Aug 2024
622Llama 3 8B Lunaris—8K$0.04013 Aug 2024
623GPT-4o (2024-08-06)—128K$2.506 Aug 2024
624Llama 3.1 8B Instruct—131K$0.05023 Jul 2024
625Llama 3.1 70B Instruct—131K$0.4023 Jul 2024
626GPT-4o-mini (2024-07-18)—128K$0.1518 Jul 2024
627Claude 3.5 Sonnet (Jun 2024)———20 Jun 2024
628Hermes 2 Theta Llama-3 70B———20 Jun 2024
629DeepSeek-Coder-V2 236B———17 Jun 2024
630DeepSeek-Coder-V2-Lite-Instruct
———13 Jun 2024
631falcon-11B-vlm
———21 May 2024
632GPT-4o—128K$2.5013 May 2024
633GPT-4o (2024-05-13)—128K$5.0013 May 2024
634Yi-1.5-34B
01.AI
———13 May 2024
635Yi-Large
01.AI
———13 May 2024
636llama3-llava-next-8b
———20 Apr 2024
637Mixtral 8x22B Instruct—66K$2.0017 Apr 2024
638WizardLM-2 8x22B—66K$0.6216 Apr 2024
639GPT-4 Turbo—128K$10.09 Apr 2024
640Qwen1.5-32B———3 Apr 2024
641DBRX
Databricks
———27 Mar 2024
642openhands-lm-32b-v0.1
———26 Mar 2024
643MM1-3B-Chat
———14 Mar 2024
644MM1-7B-Chat
———14 Mar 2024
645mistral-small-2402
———26 Feb 2024
646Gemini 1.5 Pro (Feb 2024)———15 Feb 2024
647Qwen1.5-72B———4 Feb 2024
648Qwen1.5-7B———4 Feb 2024
649Qwen1.5-14B———4 Feb 2024
650llava-v1.6-vicuna-7b
———31 Jan 2024
651llava-v1.6-vicuna-13b
———31 Jan 2024
652llava-v1.6-mistral-7b
———31 Jan 2024
653GPT-3.5 Turbo (older v0613)—4K$1.0025 Jan 2024
654GPT-4 Turbo Preview (January 2024)———25 Jan 2024
655Gemini 1.0 Pro Vision———4 Jan 2024
656instructblip-vicuna-13b
———25 Dec 2023
657InternVL-Chat-ViT-6B-Vicuna-7B
———25 Dec 2023
658Mistral 7B v0.2———11 Dec 2023
659Mistral Medium———11 Dec 2023
660GPT-4 Turbo Preview (Nov 2023)———6 Nov 2023
661llava-v1.5-7b
———5 Oct 2023
662GPT-3.5 Turbo Instruct—4K$1.5028 Sep 2023
663internlm-chat-20b
———17 Sep 2023
664Baichuan2-13B-Chat
———6 Sep 2023
665GPT-3.5 Turbo 16k—16K$3.0028 Aug 2023
666Qwen-VL-Chat
———20 Aug 2023
667Weaver (alpha)—8K$0.402 Aug 2023
668ReMM SLERP 13B—6K$0.3522 Jul 2023
669Baichuan 1-13B
Baichuan
———11 Jul 2023
670MythoMax 13B—8K$0.0802 Jul 2023
671Inflection-1———22 Jun 2023
672Vicuna-13B-v1.3
Large Model Systems Organization,University of California (UC) Berkeley
———18 Jun 2023
673GPT-3.5 Turbo (June 2023)———13 Jun 2023
674GPT-4—8K$30.028 May 2023
675GPT-3.5 Turbo—16K$0.5028 May 2023
676instructblip-vicuna-7b
———22 May 2023
677Claude 1.3———18 Apr 2023
678BLIP-2 (Q-Former)
Salesforce Research
———6 Feb 2023
Showing 78 of 678. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.← PrevExport CSV