Model intelligence

2 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

About ECI ↗

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.

2 models

2 filters:

#	Model	ECI ↓	AA idx	GPQA◆	SWE-v	FrontierMath	AIME	HLE	Terminal	Context	In $/M	Out $/M	Weights	Released
1	Mistral Medium 3.5 Mistral AI· reasoning	141.4	14.2	—	—	—	—	—	—	262K	$1.50	$7.50	Open source	28 Apr 2026
2	Mistral Small 4 Mistral AI· reasoning	—	11.3	—	—	—	—	—	—	262K	$0.15	$0.60	Open source	16 Mar 2026

Showing 2 of 2. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Export CSV