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
101Qwen3-235B-A22B-Thinking (Jul 2025)143.9——25 Jul 2025
102Qwen 3.6 35B-A3B143.9——14 Apr 2026
103DeepSeek V3.2 Exp
DeepSeek· reasoning
145.0164K$0.2729 Sep 2025
104MiniMax M2.7
MiniMax· reasoning
145.8205K$0.2118 Mar 2026
105GLM 5
Z.ai (Zhipu AI)· reasoning
145.8205K$0.6011 Feb 2026
106Kimi K2 Thinking
Moonshot AI· reasoning
146.0262K$0.606 Nov 2025
107DeepSeek V4 Flash 0423
DeepSeek· reasoning
146.11.05M$0.1424 Apr 2026
108Nemotron 3 Ultra
NVIDIA· reasoning
146.2262K$0.604 Jun 2026
109DeepSeek V3.2
DeepSeek· reasoning
146.3164K$0.281 Dec 2025
110Qwen3.6 27B
Alibaba (Qwen)· reasoning
146.5262K$0.3222 Apr 2026
111Qwen3.5 397B A17B
Alibaba (Qwen)· reasoning
146.6262K$0.5513 Feb 2026
112MiniMax M2.5
MiniMax· reasoning
146.7205K$0.2712 Feb 2026
113MiniMax M3
MiniMax· reasoning
147.01.05M$0.301 Jun 2026
114Kimi K2.5
Moonshot AI· reasoning
148.1262K$0.4527 Jan 2026
115Inkling148.6524K$1.0015 Jul 2026
116DeepSeek V4 Pro 0423
DeepSeek· reasoning
149.11.05M$0.9624 Apr 2026
117Qwen 3.8 27B149.4——14 Aug 2026
118GLM 5.1
Z.ai (Zhipu AI)· reasoning
149.9205K$1.407 Apr 2026
119Kimi K2.7 Code
Moonshot AI· reasoning
150.0262K$0.6612 Jun 2026
120Inkling Small150.1524K$0.4515 Jul 2026
121Kimi K2.6
Moonshot AI· reasoning
151.0262K$0.6520 Apr 2026
122GLM 5.2
Z.ai (Zhipu AI)· reasoning
151.81.05M$0.1416 Jun 2026
123GLM 5.3 Flash
Z.ai (Zhipu AI)· reasoning
151.91.05M$0.1520 Aug 2026
124DeepSeek V4 Flash 0731
DeepSeek· reasoning
154.51.05M$0.01831 Jul 2026
125DeepSeek V4.1 Flash
DeepSeek· reasoning
155.01.05M$0.309 Sep 2026
126DeepSeek V4 Pro 0813
DeepSeek· reasoning
155.41.05M$0.6613 Aug 2026
127GLM 5.3
Z.ai (Zhipu AI)· reasoning
155.61.05M$1.4014 Aug 2026
128Kimi K3
Moonshot AI· reasoning
157.71.05M$3.0016 Jul 2026
129MiMo-V2.6-Pro
Xiaomi· reasoning
—1.05M$0.4321 Sep 2026
130Qwen3.8 2.4T A95B
Alibaba (Qwen)· reasoning
—1.05M$2.0012 Aug 2026
131MiMo-V2.6-Flash
Xiaomi· reasoning
—1.05M$0.1421 Sep 2026
132Qwen3.8 27B
Alibaba (Qwen)· reasoning
—1M$0.4214 Aug 2026
133MiMo-V2.5-Pro
Xiaomi· reasoning
—1.05M$0.4322 Apr 2026
134Hy3 preview
Tencent· reasoning
—262K$0.1822 Apr 2026
135Ling 3.0 Flash VL—262K$0.02110 Sep 2026
136Ling 3.0 Flash—262K$0.02123 Jul 2026
137LongCat 2.0
Meituan· reasoning
—1.05M$0.3020 Jul 2026
138Qwen3.6 35B A3B
Alibaba (Qwen)· reasoning
—262K$0.1527 Apr 2026
139Qwen3.5-122B-A10B
Alibaba (Qwen)· reasoning
—262K$0.2625 Feb 2026
140DeepSeek V3.1 Terminus
DeepSeek· reasoning
—164K$0.3022 Sep 2025
141Command A—256K$2.5013 Mar 2025
142Nemotron 3.5 Lightning
NVIDIA· reasoning
—262K$0.06011 Aug 2026
143Nemotron 3 Super
NVIDIA· reasoning
—262K$0.08011 Mar 2026
144Qwen3 235B A22B Thinking 2507
Alibaba (Qwen)· reasoning
—131K$0.2325 Jul 2025
145Mistral Small 4
Mistral AI· reasoning
—262K$0.1516 Mar 2026
146Granite 4.2 8B
IBM· reasoning
—131K$0.06031 Aug 2026
147Trinity Large Thinking
Arcee AI· reasoning
—262K$0.251 Apr 2026
148Qwen3 30B A3B Thinking 2507
Alibaba (Qwen)· reasoning
—82K$0.2028 Aug 2025
149DeepSeek V3 0324—164K$0.2924 Mar 2025
150Qwen3 Coder Next—262K$0.124 Feb 2026
151Nemotron 3 Nano 30B A3B
NVIDIA· reasoning
—262K$0.05014 Dec 2025
152Devstral 2 2512—262K$0.409 Dec 2025
153Ministral 3 14B 2512—262K$0.202 Dec 2025
154Ministral 3 8B 2512—262K$0.152 Dec 2025
155Ministral 3 3B 2512—131K$0.102 Dec 2025
156Ternary Bonsai 2 27B
PrismML· reasoning
—262K$0.07518 Sep 2026
157Schematron V2 Turbo—128K$0.03012 Sep 2026
158Schematron V2 Small—128K$0.05012 Sep 2026
159Nex-N2.5-Pro
Nex AGI· reasoning
—262K$0.0758 Sep 2026
160Nex-N2.5-Mini
Nex AGI· reasoning
—262K$0.0258 Sep 2026
161Hy4 preview
Tencent· reasoning
—1.05M$0.8328 Aug 2026
162Tencent Hy4 preview (unknown)———28 Aug 2026
163Qwen3.8 Flash
Alibaba (Qwen)· reasoning
—1M$0.1526 Aug 2026
164DeepSeek V4 Flash Vision Exp
DeepSeek· reasoning
—1.05M$0.2221 Aug 2026
165Hy-MT2-1.8B—8K$0.04420 Aug 2026
166Hy-MT2-30B-A3B—8K$0.07420 Aug 2026
167GLM-5.3-Flash (unknown)———20 Aug 2026
168Hy-MT2-7B—8K$0.07419 Aug 2026
169Muse Glimmer 30B
Meta· reasoning
—131K$0.359 Aug 2026
170Laguna S 2.1
Poolside· reasoning
—1.05M$0.09021 Jul 2026
171Hy3
Tencent· reasoning
—262K$0.136 Jul 2026
172Laguna XS 2.1
Poolside· reasoning
—262K$0.0602 Jul 2026
173Nemotron 3.5 Content Safety
NVIDIA· reasoning
—131K$0.204 Jun 2026
174Step 3.7 Flash
StepFun· reasoning
—262K$0.2028 May 2026
175Laguna XS.2———28 Apr 2026
176DeepSeek v4 Pro (unknown thinking)———24 Apr 2026
177DeepSeek v4 Pro (high)———24 Apr 2026
178DeepSeek v4 (unknown)———24 Apr 2026
179DeepSeek v4 Flash (max)———24 Apr 2026
180MiMo-V2.5
Xiaomi· reasoning
—1.05M$0.1422 Apr 2026
181Reka Edge
Reka AI· reasoning
—16K$0.1020 Mar 2026
182Qwen3.5-27B
Alibaba (Qwen)· reasoning
—262K$0.2025 Feb 2026
183Qwen3.5-4B———24 Feb 2026
184Qwen3.5-2B———24 Feb 2026
185Step 3.5 Flash
StepFun· reasoning
—262K$0.1029 Jan 2026
186Kimi K2.5 (Fireworks)———27 Jan 2026
187GLM 4.7 Flash
Z.ai (Zhipu AI)· reasoning
—200K$0.06019 Jan 2026
188MiniMax M2.1
MiniMax· reasoning
—205K$0.3023 Dec 2025
189GLM-4.7 (Together)———22 Dec 2025
190GLM-4.7 (Novita)———22 Dec 2025
191GLM 4.6V
Z.ai (Zhipu AI)· reasoning
—131K$0.308 Dec 2025
192Mistral Large 3———2 Dec 2025
193DeepSeek-V3.2 (Thinking; Fireworks)———1 Dec 2025
194DeepSeek-V3.2 (Thinking; Novita)———1 Dec 2025
195DeepSeek-V3.2-Speciale———1 Dec 2025
196Kimi K2 Thinking Turbo———6 Nov 2025
197Kimi K2 Thinking (Together)———6 Nov 2025
198Voxtral Small 24B 2507—33K$0.1030 Oct 2025
199gpt-oss-safeguard-20b
OpenAI· reasoning
—131K$0.07529 Oct 2025
200MiniMax M2
MiniMax· reasoning
—205K$0.3023 Oct 2025
Showing 100 of 291. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.← PrevNext →Export CSV