Model intelligence

58 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.

58 models

2 filters:

#	Model	ECI ↑	AA idx	GPQA◆	SWE-v	FrontierMath	AIME	HLE	Terminal	Context	In $/M	Out $/M	Weights	Released
1	Gemma 3 4B Google	116.0	—	23.2	—	—	7.5	—	—	131K	$0.050	$0.10	Open source	12 Mar 2025
2	Gemma 3 12B Google	123.5	3.8	39.5	—	—	16.7	—	—	131K	$0.050	$0.15	Open source	12 Mar 2025
3	Llama 4 Scout Meta	129.6	—	51.8	—	—	7.8	—	—	1.31M	$0.10	$0.30	Open source	5 Apr 2025
4	Gemma 3 27B Google	130.0	4.9	47.7	—	—	22.5	—	—	131K	$0.080	$0.45	Open source	12 Mar 2025
5	Llama 4 Maverick Meta	132.2	—	—	—	—	—	5.7	—	1.05M	$0.19	$0.65	Open source	6 Apr 2025
6	Qwen3.5-9B Alibaba (Qwen)· reasoning	139.4	11.2	79.0	—	—	61.7	—	9.2	262K	$0.10	$0.15	Open source	24 Feb 2026
7	Mistral Medium 3.5 Mistral AI· reasoning	141.4	14.2	—	—	—	—	—	—	262K	$1.50	$7.50	Open source	28 Apr 2026
8	Gemma 4 26B A4B Google· reasoning	141.8	—	73.2	—	—	82.2	—	—	262K	$0.090	$0.30	Open source	2 Apr 2026
9	Qwen3.5-35B-A3B Alibaba (Qwen)· reasoning	142.5	—	83.5	—	—	70.0	—	—	262K	$0.16	$1.30	Open source	24 Feb 2026
10	Gemma 4 31B Google· reasoning	142.7	—	75.8	—	—	73.3	—	—	262K	$0.090	$0.34	Open source	2 Apr 2026
11	Qwen3.6 27B Alibaba (Qwen)· reasoning	146.5	21.4	85.9	—	35.1	91.1	—	—	262K	$0.32	$3.20	Open source	22 Apr 2026
12	Qwen3.5 397B A17B Alibaba (Qwen)· reasoning	146.6	18.4	86.4	—	31.2	88.9	—	—	262K	$0.55	$3.50	Open source	13 Feb 2026
13	MiniMax M3 MiniMax· reasoning	147.0	29.2	90.9	—	—	71.1	—	—	1.05M	$0.30	$1.20	Open source	1 Jun 2026
14	Kimi K2.5 Moonshot AI· reasoning	148.1	—	—	73.8	—	—	24.4	43.2	262K	$0.45	$2.25	Open source	27 Jan 2026
15	Inkling Thinking Machines Lab· reasoning	148.6	25.0	—	—	—	—	—	—	524K	$1.00	$4.05	Open source	15 Jul 2026
16	Kimi K2.7 Code Moonshot AI· reasoning	150.0	25.8	87.9	—	54.0	95.6	—	—	262K	$0.66	$3.30	Open source	12 Jun 2026
17	Inkling Small Thinking Machines Lab· reasoning	150.1	—	—	—	—	—	—	—	524K	$0.45	$1.20	Open source	15 Jul 2026
18	Kimi K2.6 Moonshot AI· reasoning	151.0	27.0	90.8	76.7	57.2	96.1	—	—	262K	$0.65	$3.41	Open source	20 Apr 2026
19	GLM 5.3 Flash Z.ai (Zhipu AI)· reasoning	151.9	41.8	90.2	—	55.8	93.9	—	—	1.31M	$0.15	$0.50	Open source	20 Aug 2026
20	DeepSeek V4.1 Flash DeepSeek· reasoning	155.0	39.5	—	—	—	—	—	—	1.05M	$0.30	$1.20	Open source	9 Sep 2026
21	Kimi K3 Moonshot AI· reasoning	157.7	43.6	93.1	—	72.2	97.2	—	—	1.05M	$3.00	$15.0	Open source	16 Jul 2026
22	MiMo-V2.6-Pro Xiaomi· reasoning	—	46.3	—	—	—	—	—	—	1.05M	$0.43	$0.87	Open source	21 Sep 2026
23	MiMo-V2.6-Flash Xiaomi· reasoning	—	37.9	—	—	—	—	—	—	1.05M	$0.14	$0.28	Open source	21 Sep 2026
24	Qwen3.8 27B Alibaba (Qwen)· reasoning	—	33.7	—	—	—	—	—	—	1M	$0.053	$4.40	Open source	14 Aug 2026
25	Ling 3.0 Flash VL inclusionAI (Ant Group)· reasoning	—	24.6	—	—	—	—	—	—	262K	$0.021	$0.062	Open source	10 Sep 2026
26	Qwen3.6 35B A3B Alibaba (Qwen)· reasoning	—	18.2	84.8	—	20.4	86.7	—	23.0	262K	$0.15	$1.00	Open source	27 Apr 2026
27	Qwen3.5-122B-A10B Alibaba (Qwen)· reasoning	—	15.6	—	—	—	—	—	—	262K	$0.26	$2.08	Open source	25 Feb 2026
28	Mistral Small 4 Mistral AI· reasoning	—	11.3	—	—	—	—	—	—	262K	$0.15	$0.60	Open source	16 Mar 2026
29	Ministral 3 14B 2512 Mistral AI	—	6.0	—	—	—	—	—	—	262K	$0.20	$0.20	Open source	2 Dec 2025
30	Ministral 3 8B 2512 Mistral AI	—	5.5	—	—	—	—	—	—	262K	$0.15	$0.15	Open source	2 Dec 2025
31	Ministral 3 3B 2512 Mistral AI	—	4.8	—	—	—	—	—	—	131K	$0.10	$0.10	Open source	2 Dec 2025
32	Ternary Bonsai 2 27B PrismML· reasoning	—	—	—	—	—	—	—	—	262K	$0.075	$0.50	Open source	18 Sep 2026
33	Nex-N2.5-Pro Nex AGI· reasoning	—	—	—	—	—	—	—	—	262K	$0.075	$0.25	Open source	8 Sep 2026
34	Nex-N2.5-Mini Nex AGI· reasoning	—	—	—	—	—	—	—	—	262K	$0.025	$0.10	Open source	8 Sep 2026
35	Qwen3.8 Flash Alibaba (Qwen)· reasoning	—	—	—	—	—	—	—	—	1M	$0.15	$0.47	Open source	26 Aug 2026
36	DeepSeek V4 Flash Vision Exp DeepSeek· reasoning	—	—	—	—	—	—	—	—	1.05M	$0.22	$0.65	Open source	21 Aug 2026
37	Muse Glimmer 30B Meta· reasoning	—	—	—	—	—	—	—	—	131K	$0.30	$1.20	Open source	9 Aug 2026
38	Nemotron 3.5 Content Safety NVIDIA· reasoning	—	—	—	—	—	—	—	—	131K	$0.20	$0.20	Open source	4 Jun 2026
39	Step 3.7 Flash StepFun· reasoning	—	—	—	—	—	—	—	—	262K	$0.20	$1.15	Open source	28 May 2026
40	MiMo-V2.5 Xiaomi· reasoning	—	—	—	—	—	—	—	—	1.05M	$0.14	$0.28	Open source	22 Apr 2026
41	Reka Edge Reka AI· reasoning	—	—	—	—	—	—	—	—	16K	$0.10	$0.10	Open source	20 Mar 2026
42	Qwen3.5-27B Alibaba (Qwen)· reasoning	—	—	—	—	—	—	—	—	262K	$0.20	$1.56	Open source	25 Feb 2026
43	GLM 4.6V Z.ai (Zhipu AI)· reasoning	—	—	—	—	—	—	—	—	131K	$0.30	$0.90	Open source	8 Dec 2025
44	Qwen3 VL 32B Instruct Alibaba (Qwen)	—	—	—	—	—	—	—	—	131K	$0.10	$0.42	Open source	23 Oct 2025
45	Qwen3 VL 8B Thinking Alibaba (Qwen)· reasoning	—	—	—	—	—	—	—	—	131K	$0.18	$2.10	Open source	14 Oct 2025
46	Qwen3 VL 8B Instruct Alibaba (Qwen)	—	—	—	—	—	—	—	—	262K	$0.12	$0.46	Open source	14 Oct 2025
47	Qwen3 VL 30B A3B Thinking Alibaba (Qwen)· reasoning	—	—	—	—	—	—	—	—	262K	$0.20	$2.40	Open source	6 Oct 2025
48	Qwen3 VL 30B A3B Instruct Alibaba (Qwen)	—	—	—	—	—	—	—	—	262K	$0.15	$0.60	Open source	6 Oct 2025
49	Qwen3 VL 235B A22B Thinking Alibaba (Qwen)· reasoning	—	—	—	—	—	—	—	—	131K	$0.40	$4.00	Open source	23 Sep 2025
50	Qwen3 VL 235B A22B Instruct Alibaba (Qwen)	—	—	—	—	—	—	—	—	262K	$0.21	$1.90	Open source	23 Sep 2025
51	GLM 4.5V Z.ai (Zhipu AI)· reasoning	—	—	—	—	—	—	—	—	66K	$0.60	$1.80	Open source	11 Aug 2025
52	UI-TARS 7B ByteDance	—	—	—	—	—	—	—	—	128K	$0.10	$0.20	Open source	22 Jul 2025
53	ERNIE 4.5 VL 424B A47B Baidu· reasoning	—	—	—	—	—	—	—	—	123K	$0.42	$1.25	Open source	30 Jun 2025
54	Mistral Small 3.2 24B Mistral AI	—	—	—	—	—	—	—	—	256K	$0.094	$0.25	Open source	20 Jun 2025
55	Llama Guard 4 12B Meta	—	—	—	—	—	—	—	—	164K	$0.18	$0.18	Open source	30 Apr 2025
56	Mistral Small 3.1 24B Mistral AI	—	—	—	—	—	—	—	—	128K	$0.35	$0.56	Open source	17 Mar 2025
57	Qwen2.5 VL 72B Instruct Alibaba (Qwen)	—	—	—	—	—	—	—	—	128K	$0.80	$1.00	Open source	1 Feb 2025
58	MiniMax-01 MiniMax	—	—	—	—	—	—	—	—	1M	$0.20	$1.10	Open source	15 Jan 2025

Showing 58 of 58. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Export CSV