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.
Only models with both an ECI score and an OpenRouter price. Normalisation: 75% input + 25% output price. Click a point to open the model.
| # | Model | ECI ↑ | Context | In $/M | Weights | Released |
|---|---|---|---|---|---|---|
| 101 | Claude 3.5 Haiku | 127.2 | — | — | Closed | 22 Oct 2024 |
| 102 | GPT-4 Turbo (Apr 2024) | 127.3 | — | — | Closed | 9 Apr 2024 |
| 103 | Llama 3.3 70B | 127.3 | — | — | Open source | 6 Dec 2024 |
| 104 | Mistral Small 3.1 | 127.5 | — | — | Open source | 17 Mar 2025 |
| 105 | Mistral Large 2 (Jul 2024) | 127.5 | — | — | Open source | 24 Jul 2024 |
| 106 | Mistral Large 2 (Nov 2024) | 128.5 | — | — | Open source | 18 Nov 2024 |
| 107 | Qwen2.5-32B | 128.5 | — | — | Open source | 17 Sep 2024 |
| 108 | Llama 3.1-405B | 128.8 | — | — | Open source | 23 Jul 2024 |
| 109 | GPT-4o (Aug 2024) | 128.8 | — | — | Closed | 6 Aug 2024 |
| 110 | GPT-4o (Nov 2024) | 128.8 | — | — | Closed | 20 Nov 2024 |
| 111 | GPT-4o (May 2024) | 129.0 | — | — | Closed | 13 May 2024 |
| 112 | Qwen2.5-72B | 129.0 | — | — | Open source | 19 Sep 2024 |
| 113 | Gemini 1.5 Flash (Sep 2024) | 129.4 | — | — | Closed | 24 Sep 2024 |
| 114 | GPT-4.1 Nano | 129.6 | 1.05M | $0.10 | Closed | 14 Apr 2025 |
| 115 | Llama 4 Scout | 129.6 | 1.31M | $0.10 | Open source | 5 Apr 2025 |
| 116 | Claude 3.5 Sonnet | 130.0 | — | — | Closed | 20 Jun 2024 |
| 117 | Gemma 3 27B | 130.0 | 131K | $0.080 | Open source | 12 Mar 2025 |
| 118 | Phi 4 | 130.4 | 16K | $0.070 | Open source | 12 Dec 2024 |
| 119 | Grok-2 (Dec 2024) | 130.5 | — | — | Closed | 12 Dec 2024 |
| 120 | Magistral Small 1.2 | 131.4 | — | — | Open source | 18 Sep 2025 |
| 121 | Mistral Small 3.2 | 131.7 | — | — | Open source | 20 Jun 2025 |
| 122 | Gemini 1.5 Pro (Sept 2024) | 131.7 | — | — | Closed | 24 Sep 2024 |
| 123 | Llama 4 Maverick | 132.2 | 1.05M | $0.19 | Open source | 6 Apr 2025 |
| 124 | DeepSeek V3 | 132.4 | 164K | $0.26 | Open source | 26 Dec 2024 |
| 125 | Qwen2.5-Max | 132.5 | — | — | Closed | 25 Jan 2025 |
| 126 | Magistral Small 1.0 | 133.2 | — | — | Open source | 10 Jun 2025 |
| 127 | Claude 3.5 Sonnet (October 2024) | 133.6 | — | — | Closed | 22 Oct 2024 |
| 128 | Gemini 2.5 Flash-Lite (Jun 2025) | 133.9 | — | — | Closed | 17 Jun 2025 |
| 129 | Mistral Medium 3 | 134.1 | 131K | $0.40 | Closed | 7 May 2025 |
| 130 | Gemini 2.0 Flash (Feb 2025) | 134.7 | — | — | Closed | 5 Feb 2025 |
| 131 | Gemini 2.0 Flash (Dec 2024) | 134.7 | — | — | Closed | 11 Dec 2024 |
| 132 | o1-preview | 134.8 | — | — | Closed | 12 Sep 2024 |
| 133 | GPT-4.1 Mini | 135.0 | 1.05M | $0.40 | Closed | 14 Apr 2025 |
| 134 | Gemini 2.0 Pro | 135.1 | — | — | Closed | 5 Feb 2025 |
| 135 | Gemini 2.0 Flash Thinking (Jan 2025) | 135.4 | — | — | Closed | 21 Jan 2025 |
| 136 | DeepSeek-R1-Distill-Qwen-14B | 135.4 | — | — | Open source | 20 Jan 2025 |
| 137 | o1-mini | 135.8 | — | — | Closed | 12 Sep 2024 |
| 138 | DeepSeek-V3 (Mar 2025) | 135.9 | — | — | Open source | 24 Mar 2025 |
| 139 | Qwen3 8B Alibaba (Qwen)· reasoning | 136.2 | 131K | $0.12 | Open source | 28 Apr 2025 |
| 140 | Qwen3 30B A3B Alibaba (Qwen)· reasoning | 136.2 | 131K | $0.12 | Open source | 29 Apr 2025 |
| 141 | GPT-4.5 | 136.7 | — | — | Closed | 27 Feb 2025 |
| 142 | GPT-4.1 | 136.8 | 1.05M | $2.00 | Closed | 14 Apr 2025 |
| 143 | Qwen3-30B-A3B-Instruct (Jul 2025) | 137.4 | — | — | Open source | 29 Jul 2025 |
| 144 | DeepSeek-R1-Distill-Qwen-32B | 137.4 | — | — | Open source | 20 Jan 2025 |
| 145 | QwQ-32B | 137.6 | — | — | Open source | 5 Mar 2025 |
| 146 | gpt-oss-20b OpenAI· reasoning | 137.8 | 131K | $0.018 | Open source | 5 Aug 2025 |
| 147 | Qwen3 14B Alibaba (Qwen)· reasoning | 138.2 | 131K | $0.12 | Open source | 29 Apr 2025 |
| 148 | Grok 3 | 138.3 | — | — | Closed | 9 Apr 2025 |
| 149 | Qwen3 32B Alibaba (Qwen)· reasoning | 138.5 | 131K | $0.080 | Open source | 29 Apr 2025 |
| 150 | Qwen3-235B-A22B-Instruct (Jul 2025) | 138.9 | — | — | Open source | 25 Jul 2025 |
| 151 | R1 DeepSeek· reasoning | 139.0 | 64K | $0.70 | Open source | 20 Jan 2025 |
| 152 | Qwen3 235B A22B Alibaba (Qwen)· reasoning | 139.4 | 131K | $0.46 | Open source | 28 Apr 2025 |
| 153 | GPT-5 Nano OpenAI· reasoning | 139.4 | 400K | $0.050 | Closed | 7 Aug 2025 |
| 154 | Qwen3.5-9B Alibaba (Qwen)· reasoning | 139.4 | 262K | $0.10 | Open source | 24 Feb 2026 |
| 155 | Qwen3-30B-A3B-Thinking (Jul 2025) | 139.6 | — | — | Open source | 30 Jul 2025 |
| 156 | DeepSeek V3.1 DeepSeek· reasoning | 139.9 | 164K | $0.25 | Open source | 21 Aug 2025 |
| 157 | gpt-oss-120b OpenAI· reasoning | 139.9 | 131K | $0.15 | Open source | 5 Aug 2025 |
| 158 | Gemini 2.5 Flash (Apr 2025) | 140.0 | — | — | Closed | 17 Apr 2025 |
| 159 | Kimi K2 (Jul 2025) | 140.1 | — | — | Open source | 12 Jul 2025 |
| 160 | Grok-3 mini | 140.3 | — | — | Closed | 24 Jun 2025 |
| 161 | o3 Mini OpenAI· reasoning | 140.3 | 200K | $1.10 | Closed | 31 Jan 2025 |
| 162 | Gemini 2.5 Flash (Jun 2025) | 140.8 | — | — | Closed | 17 Jun 2025 |
| 163 | Claude 3.7 Sonnet | 141.2 | — | — | Closed | 24 Feb 2025 |
| 164 | DeepSeek-R1 (May 2025) | 141.3 | — | — | Open source | 28 May 2025 |
| 165 | Mistral Medium 3.5 Mistral AI· reasoning | 141.4 | 262K | $1.50 | Open source | 28 Apr 2026 |
| 166 | Gemini 2.5 Flash (May 2025) | 141.5 | — | — | Closed | 20 May 2025 |
| 167 | Claude Sonnet 4 Anthropic· reasoning | 141.7 | 200K | $3.00 | Closed | 22 May 2025 |
| 168 | Gemma 4 26B A4B Google· reasoning | 141.8 | 262K | $0.090 | Open source | 2 Apr 2026 |
| 169 | o1 OpenAI· reasoning | 141.9 | 200K | $15.0 | Closed | 17 Dec 2024 |
| 170 | Qwen3 Max Alibaba (Qwen)· reasoning | 142.4 | 262K | $0.78 | Closed | 24 Sep 2025 |
| 171 | Claude Haiku 4.5 Anthropic· reasoning | 142.4 | 200K | $1.00 | Closed | 15 Oct 2025 |
| 172 | Gemini 2.5 Pro (May 2025) | 142.5 | — | — | Closed | 6 May 2025 |
| 173 | GPT-5.5 Instant | 142.5 | — | — | Closed | 5 May 2026 |
| 174 | Qwen3.5-35B-A3B Alibaba (Qwen)· reasoning | 142.5 | 262K | $0.16 | Open source | 24 Feb 2026 |
| 175 | Claude Opus 4 | 142.7 | — | — | Closed | 22 May 2025 |
| 176 | Gemma 4 31B Google· reasoning | 142.7 | 262K | $0.090 | Open source | 2 Apr 2026 |
| 177 | Gemini 2.5 Flash (Sep 2025) | 143.0 | — | — | Closed | 25 Sep 2025 |
| 178 | Qwen 3.6 Flash | 143.3 | — | — | Closed | 27 Apr 2026 |
| 179 | GLM 4.7 Z.ai (Zhipu AI)· reasoning | 143.5 | 205K | $0.60 | Open source | 22 Dec 2025 |
| 180 | Qwen3-235B-A22B-Thinking (Jul 2025) | 143.9 | — | — | Open source | 25 Jul 2025 |
| 181 | Qwen 3.6 35B-A3B | 143.9 | — | — | Open source | 14 Apr 2026 |
| 182 | Qwen 3.5 Flash (hosted 35B-A3B) | 144.0 | — | — | Closed | 25 Feb 2026 |
| 183 | Claude Opus 4.1 Anthropic· reasoning | 144.1 | 200K | $15.0 | Closed | 5 Aug 2025 |
| 184 | Gemini 2.5 Pro (Mar 2025) | 144.2 | — | — | Closed | 31 Mar 2025 |
| 185 | Grok 4 Fast | 144.2 | — | — | Closed | 19 Sep 2025 |
| 186 | Gemini 3.1 Flash Lite Google· reasoning | 144.4 | 1.05M | $0.25 | Closed | 3 Mar 2026 |
| 187 | Qwen3.7 Flash Alibaba (Qwen)· reasoning | 144.6 | 1M | $0.030 | Closed | 27 Jul 2026 |
| 188 | DeepSeek V3.2 Exp DeepSeek· reasoning | 145.0 | 164K | $0.13 | Open source | 29 Sep 2025 |
| 189 | Gemini 3.5 Flash Lite Google· reasoning | 145.1 | 1.05M | $0.30 | Closed | 21 Jul 2026 |
| 190 | Gemini 2.5 Pro (Jun 2025) | 145.3 | — | — | Closed | 5 Jun 2025 |
| 191 | GPT-5 Mini OpenAI· reasoning | 145.5 | 400K | $0.25 | Closed | 7 Aug 2025 |
| 192 | o4 Mini OpenAI· reasoning | 145.6 | 200K | $1.10 | Closed | 16 Apr 2025 |
| 193 | GPT-5.4 Nano OpenAI· reasoning | 145.8 | 400K | $0.20 | Closed | 17 Mar 2026 |
| 194 | MiniMax M2.7 MiniMax· reasoning | 145.8 | 205K | $0.30 | Open source | 18 Mar 2026 |
| 195 | GLM 5 Z.ai (Zhipu AI)· reasoning | 145.8 | 205K | $0.60 | Open source | 11 Feb 2026 |
| 196 | Kimi K2 Thinking Moonshot AI· reasoning | 146.0 | 262K | $0.60 | Open source | 6 Nov 2025 |
| 197 | DeepSeek V4 Flash 0423 DeepSeek· reasoning | 146.1 | 1.05M | $0.062 | Open source | 24 Apr 2026 |
| 198 | Nemotron 3 Ultra NVIDIA· reasoning | 146.2 | 262K | $0.60 | Open source | 4 Jun 2026 |
| 199 | DeepSeek V3.2 DeepSeek· reasoning | 146.3 | 164K | $0.28 | Open source | 1 Dec 2025 |
| 200 | Grok 4 | 146.5 | — | — | Closed | 9 Jul 2025 |