Skip to content
Model intelligence

99 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
1Qwen3.7 Flash
Alibaba (Qwen)· reasoning
144.61M$0.03027 Jul 2026
2Gemini 3.5 Flash Lite
Google· reasoning
145.11.05M$0.3021 Jul 2026
3Inkling148.6524K$1.0015 Jul 2026
4Qwen 3.8 27B149.4——14 Aug 2026
5Inkling Small150.1524K$0.4515 Jul 2026
6GLM 5.3 Flash
Z.ai (Zhipu AI)· reasoning
151.91.31M$0.1520 Aug 2026
7Grok 4.5
xAI· reasoning
154.0500K$2.008 Jul 2026
8Muse Spark 1.1
Meta· reasoning
154.31.05M$1.259 Jul 2026
9Gemini 3.6 Flash
Google· reasoning
154.41.05M$0.7521 Jul 2026
10DeepSeek V4 Flash 0731
DeepSeek· reasoning
154.51.31M$0.01831 Jul 2026
11DeepSeek V4.1 Flash
DeepSeek· reasoning
155.01.05M$0.309 Sep 2026
12Muse Spark 1.2
Meta· reasoning
155.21.05M$1.255 Aug 2026
13Qwen3.8 Max (0902)
Alibaba (Qwen)· reasoning
155.31M$2.001 Sep 2026
14DeepSeek V4 Pro 0813
DeepSeek· reasoning
155.41.05M$0.4813 Aug 2026
15GLM 5.3
Z.ai (Zhipu AI)· reasoning
155.61.31M$1.4014 Aug 2026
16GPT-5.6 Luna
OpenAI· reasoning
156.31.05M$0.209 Jul 2026
17Grok 4.6
xAI· reasoning
156.5500K$2.0012 Aug 2026
18Qwen 3.8 Max156.7——2 Aug 2026
19Muse Spark 1.3
Meta· reasoning
156.91.05M$1.252 Sep 2026
20Gemini 3.8 Flash
Google· reasoning
157.11.05M$0.752 Sep 2026
21Kimi K3
Moonshot AI· reasoning
157.71.05M$3.0016 Jul 2026
22Gemini 3.7 Flash
Google· reasoning
157.71.05M$0.7513 Aug 2026
23GPT-5.6 Terra
OpenAI· reasoning
159.31.05M$2.009 Jul 2026
24GPT-5.6 Sol
OpenAI· reasoning
162.01.05M$2.009 Jul 2026
25Claude Opus 5
Anthropic· reasoning
162.71M$5.0024 Jul 2026
26Claude Fable 5.1
Anthropic· reasoning
165.01M$10.01 Sep 2026
27GPT-6 Astra
OpenAI· reasoning
166.61.05M$10.03 Sep 2026
28Claude Opus 5.5
Anthropic· reasoning
—1M$4.0022 Sep 2026
29Claude Sonnet 5.5
Anthropic· reasoning
—1M$2.0028 Sep 2026
30GPT-6 Sol
OpenAI· reasoning
—1.05M$2.0022 Sep 2026
31Grok 4.7
xAI· reasoning
—500K$2.0021 Sep 2026
32MiMo-V2.6-Pro
Xiaomi· reasoning
—1.05M$0.4321 Sep 2026
33Qwen3.8 2.4T A95B
Alibaba (Qwen)· reasoning
—1.05M$2.0012 Aug 2026
34MiMo-V2.6-Flash
Xiaomi· reasoning
—1.05M$0.1421 Sep 2026
35GPT-6 Luna
OpenAI· reasoning
—1.05M$0.1022 Sep 2026
36Qwen3.8 27B
Alibaba (Qwen)· reasoning
—1M$0.05314 Aug 2026
37Ling 3.0 Flash VL—262K$0.02110 Sep 2026
38Ling 3.0 Flash Fin—262K$0.06027 Aug 2026
39LongCat 2.0
Meituan· reasoning
—1.05M$0.3020 Jul 2026
40Nemotron 3.5 Lightning
NVIDIA· reasoning
—1M$0.06011 Aug 2026
41Mercury 2.5
Inception Labs· reasoning
—260K$0.0408 Sep 2026
42Granite 4.2 8B
IBM· reasoning
—131K$0.06031 Aug 2026
43Jev Router—1M—25 Sep 2026
44Perceptron Mk1.5
Perceptron· reasoning
—37K$0.1525 Sep 2026
45Ember-1
Fireworks AI· reasoning
—1.05M$3.0024 Sep 2026
46GLM 5.3 Prime
Z.ai (Zhipu AI)· reasoning
—1M$2.8023 Sep 2026
47Aion 3.5
AionLabs· reasoning
—262K$3.0023 Sep 2026
48Solar Mini 4
Upstage· reasoning
—524K$0.05023 Sep 2026
49Qwen3.8 Max Prime
Alibaba (Qwen)· reasoning
—1M$4.0023 Sep 2026
50Aion 3.5 Mini
AionLabs· reasoning
—262K$0.7023 Sep 2026
51GPT-6 Sol Pro
OpenAI· reasoning
—1.05M$2.0022 Sep 2026
52GPT-6 Luna Pro
OpenAI· reasoning
—1.05M$0.1022 Sep 2026
53Qwen3.8 Omni Flash
Alibaba (Qwen)· reasoning
—1M$0.1521 Sep 2026
54MiMo-V2.6-Pro-UltraSpeed
Xiaomi· reasoning
—1.05M$4.3521 Sep 2026
55GLM 5.3 FlashX
Z.ai (Zhipu AI)· reasoning
—1.05M$0.3718 Sep 2026
56Ternary Bonsai 2 27B
PrismML· reasoning
—262K$0.07518 Sep 2026
57Pareto—262K$2.5017 Sep 2026
58Schematron V2 Turbo—128K$0.03012 Sep 2026
59Schematron V2 Small—128K$0.05012 Sep 2026
60Fugu Max
Sakana AI· reasoning
—1M$2.0011 Sep 2026
61Fugu Ultra v2
Sakana AI· reasoning
—1M$5.0011 Sep 2026
62SWE-2 (max)———10 Sep 2026
63Nex-N2.5-Pro
Nex AGI· reasoning
—262K$0.0758 Sep 2026
64Nex-N2.5-Mini
Nex AGI· reasoning
—262K$0.0258 Sep 2026
65GPT-6 Astra Pro
OpenAI· reasoning
—1.05M$10.04 Sep 2026
66GPT-6 Astra (pro, max)———3 Sep 2026
67Muse Spark 1.3 Contributor
Meta· reasoning
—1.05M$0.102 Sep 2026
68Hy4 preview
Tencent· reasoning
—1.05M$0.8328 Aug 2026
69Tencent Hy4 preview (unknown)———28 Aug 2026
70Qwen3.8 Flash
Alibaba (Qwen)· reasoning
—1M$0.1526 Aug 2026
71Muse Spark 1.2 Contributor
Meta· reasoning
—1.05M$0.1021 Aug 2026
72DeepSeek V4 Flash Vision Exp
DeepSeek· reasoning
—1.05M$0.2221 Aug 2026
73Hy-MT2-1.8B—8K$0.04420 Aug 2026
74Hy-MT2-30B-A3B—8K$0.07420 Aug 2026
75GLM-5.3-Flash (unknown)———20 Aug 2026
76Hy-MT2-7B—8K$0.07419 Aug 2026
77GLM-5.3 (unknown thinking)———14 Aug 2026
78Seed-2.0-Code
ByteDance· reasoning
—262K$0.5012 Aug 2026
79Seed 2.1 Turbo
ByteDance· reasoning
—262K$0.5012 Aug 2026
80Sakana Namazu
Sakana AI· reasoning
—262K$0.9511 Aug 2026
81Solar Pro 4
Upstage· reasoning
—524K$0.09010 Aug 2026
82Muse Glimmer 30B
Meta· reasoning
—131K$0.309 Aug 2026
83Qwen3.8 Max (xhigh)———2 Aug 2026
84Qwen3.8 Max (unknown)———2 Aug 2026
85Ling 3.0 Flash—262K$0.02123 Jul 2026
86Laguna S 2.1
Poolside· reasoning
—1.05M$0.09021 Jul 2026
87Gemini 3.5 Flash-Lite (medium)———21 Jul 2026
88KAT-Coder-Pro V2.5—262K$0.7410 Jul 2026
89GPT-5.6 Sol Pro
OpenAI· reasoning
—1.05M$4.009 Jul 2026
90GPT-5.6 Luna Pro
OpenAI· reasoning
—1.05M$0.209 Jul 2026
91GPT-5.6 Terra Pro
OpenAI· reasoning
—1.05M$2.009 Jul 2026
92GPT-5.6 Sol (pro, max)———9 Jul 2026
93GPT-5.6 Sol (pro, xhigh)———9 Jul 2026
94GPT-5.6 Sol (pro, unknown thinking)———9 Jul 2026
95SWE-1.7———8 Jul 2026
96Aion-3.0
AionLabs· reasoning
—131K$3.007 Jul 2026
97Aion-3.0-Mini
AionLabs· reasoning
—131K$0.707 Jul 2026
98Hy3
Tencent· reasoning
—262K$0.136 Jul 2026
99Laguna XS 2.1
Poolside· reasoning
—262K$0.0602 Jul 2026
Showing 99 of 99. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Export CSV