Skip to content
Model intelligence

291 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
1Kimi K3
Moonshot AI· reasoning
157.71.05M$3.0016 Jul 2026
2GLM 5.3
Z.ai (Zhipu AI)· reasoning
155.61.05M$1.4014 Aug 2026
3DeepSeek V4 Pro 0813
DeepSeek· reasoning
155.41.05M$0.6613 Aug 2026
4DeepSeek V4.1 Flash
DeepSeek· reasoning
155.01.05M$0.309 Sep 2026
5DeepSeek V4 Flash 0731
DeepSeek· reasoning
154.51.05M$0.01831 Jul 2026
6GLM 5.3 Flash
Z.ai (Zhipu AI)· reasoning
151.91.05M$0.1520 Aug 2026
7GLM 5.2
Z.ai (Zhipu AI)· reasoning
151.81.05M$0.1416 Jun 2026
8Kimi K2.6
Moonshot AI· reasoning
151.0262K$0.6520 Apr 2026
9Inkling Small150.1524K$0.4515 Jul 2026
10Kimi K2.7 Code
Moonshot AI· reasoning
150.0262K$0.6612 Jun 2026
11GLM 5.1
Z.ai (Zhipu AI)· reasoning
149.9205K$1.407 Apr 2026
12Qwen 3.8 27B149.4——14 Aug 2026
13DeepSeek V4 Pro 0423
DeepSeek· reasoning
149.11.05M$0.9624 Apr 2026
14Inkling148.6524K$1.0015 Jul 2026
15Kimi K2.5
Moonshot AI· reasoning
148.1262K$0.4527 Jan 2026
16MiniMax M3
MiniMax· reasoning
147.01.05M$0.301 Jun 2026
17MiniMax M2.5
MiniMax· reasoning
146.7205K$0.2712 Feb 2026
18Qwen3.5 397B A17B
Alibaba (Qwen)· reasoning
146.6262K$0.5513 Feb 2026
19Qwen3.6 27B
Alibaba (Qwen)· reasoning
146.5262K$0.3222 Apr 2026
20DeepSeek V3.2
DeepSeek· reasoning
146.3164K$0.281 Dec 2025
21Nemotron 3 Ultra
NVIDIA· reasoning
146.2262K$0.604 Jun 2026
22DeepSeek V4 Flash 0423
DeepSeek· reasoning
146.11.05M$0.1424 Apr 2026
23Kimi K2 Thinking
Moonshot AI· reasoning
146.0262K$0.606 Nov 2025
24MiniMax M2.7
MiniMax· reasoning
145.8205K$0.2118 Mar 2026
25GLM 5
Z.ai (Zhipu AI)· reasoning
145.8205K$0.6011 Feb 2026
26DeepSeek V3.2 Exp
DeepSeek· reasoning
145.0164K$0.2729 Sep 2025
27Qwen 3.6 35B-A3B143.9——14 Apr 2026
28Qwen3-235B-A22B-Thinking (Jul 2025)143.9——25 Jul 2025
29GLM 4.7
Z.ai (Zhipu AI)· reasoning
143.5205K$0.6022 Dec 2025
30Gemma 4 31B
Google· reasoning
142.7262K$0.0902 Apr 2026
31Qwen3.5-35B-A3B
Alibaba (Qwen)· reasoning
142.5262K$0.1624 Feb 2026
32Gemma 4 26B A4B
Google· reasoning
141.8262K$0.0762 Apr 2026
33Mistral Medium 3.5
Mistral AI· reasoning
141.4262K$1.5028 Apr 2026
34DeepSeek-R1 (May 2025)141.3——28 May 2025
35Kimi K2 (Jul 2025)140.1——12 Jul 2025
36gpt-oss-120b
OpenAI· reasoning
139.9131K$0.0375 Aug 2025
37DeepSeek V3.1
DeepSeek· reasoning
139.9164K$0.2521 Aug 2025
38Qwen3-30B-A3B-Thinking (Jul 2025)139.6——30 Jul 2025
39Qwen3.5-9B
Alibaba (Qwen)· reasoning
139.4262K$0.1024 Feb 2026
40Qwen3 235B A22B
Alibaba (Qwen)· reasoning
139.4131K$0.4628 Apr 2025
41R1
DeepSeek· reasoning
139.064K$0.7020 Jan 2025
42Qwen3-235B-A22B-Instruct (Jul 2025)138.9——25 Jul 2025
43Qwen3 32B
Alibaba (Qwen)· reasoning
138.5131K$0.08029 Apr 2025
44Qwen3 14B
Alibaba (Qwen)· reasoning
138.2131K$0.1229 Apr 2025
45gpt-oss-20b
OpenAI· reasoning
137.8131K$0.0185 Aug 2025
46QwQ-32B137.6——5 Mar 2025
47DeepSeek-R1-Distill-Qwen-32B137.4——20 Jan 2025
48Qwen3-30B-A3B-Instruct (Jul 2025)137.4——29 Jul 2025
49Qwen3 30B A3B
Alibaba (Qwen)· reasoning
136.2131K$0.1329 Apr 2025
50Qwen3 8B
Alibaba (Qwen)· reasoning
136.2131K$0.1228 Apr 2025
51DeepSeek-V3 (Mar 2025)135.9——24 Mar 2025
52DeepSeek-R1-Distill-Qwen-14B135.4——20 Jan 2025
53Magistral Small 1.0133.2——10 Jun 2025
54DeepSeek V3132.4164K$0.2626 Dec 2024
55Llama 4 Maverick132.21.05M$0.196 Apr 2025
56Mistral Small 3.2131.7——20 Jun 2025
57Magistral Small 1.2131.4——18 Sep 2025
58Phi 4130.416K$0.07012 Dec 2024
59Gemma 3 27B130.0131K$0.08012 Mar 2025
60Llama 4 Scout129.61.31M$0.105 Apr 2025
61Qwen2.5-72B129.0——19 Sep 2024
62Llama 3.1-405B128.8——23 Jul 2024
63Mistral Large 2 (Nov 2024)128.5——18 Nov 2024
64Qwen2.5-32B128.5——17 Sep 2024
65Mistral Large 2 (Jul 2024)127.5——24 Jul 2024
66Mistral Small 3.1127.5——17 Mar 2025
67Llama 3.3 70B127.3——6 Dec 2024
68Mistral Small 3127.133K$0.05030 Jan 2025
69Llama 3.1-70B125.9——23 Jul 2024
70Llama 3.2 90B125.5——24 Sep 2024
71Qwen2-72B125.3——7 Jun 2024
72DeepSeek-V2 (MoE-236B, May 2024)124.8——7 May 2024
73Gemma 3 12B123.5131K$0.05012 Mar 2025
74Llama 3-70B122.9——18 Apr 2024
75Gemma 2 27B122.18K$0.6524 Jun 2024
76Mixtral 8x22B122.0——17 Apr 2024
77phi-3-small 7.4B121.8——23 Apr 2024
78phi-3-medium 14B121.2——23 Apr 2024
79Gemma 2 9B119.8——24 Jun 2024
80Qwen2.5-Coder-32B119.4——18 Sep 2024
81Command R+119.3——30 Aug 2024
82Mistral Nemo118.6131K$0.01918 Jul 2024
83Qwen2.5-7B118.4——19 Sep 2024
84Mixtral 8x7B118.4——11 Dec 2023
85Yi-34B
01.AI
117.3——2 Nov 2023
86phi-3-mini 3.8B117.2——23 Apr 2024
87Stable Beluga 2117.0——20 Jul 2023
88Llama 3.1-8B116.5——23 Jul 2024
89Llama 3-8B116.3——18 Apr 2024
90Gemma 3 4B116.0131K$0.05012 Mar 2025
91Llama 2-70B113.6——18 Jul 2023
92Qwen2.5-Coder (7B)112.9——18 Sep 2024
93Qwen-14B112.8——24 Sep 2023
94Mistral 7B v0.1112.0——27 Sep 2023
95Falcon-180B111.9——6 Sep 2023
96Gemma 7B111.7——21 Feb 2024
97DeepSeek LLM 67B110.5——29 Nov 2023
98LLaMA-65B109.9——24 Feb 2023
99Falcon 2 11B109.3——9 May 2024
100Mistral 7B v0.3108.7——27 May 2024
Showing 100 of 291. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Next →Export CSV