Epoch ECI leaderboard: which LLMs score highest
Epoch ECI (Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks) currently has scores for 205 models. The top score is 157 by Qwen 3.8 Max; the median model scores 127 and the lowest scores 56.
| # | Model | Organisation | Epoch ECI score | Cheapest input $/M | Source | Captured |
|---|---|---|---|---|---|---|
| 1 | Qwen 3.8 Max | Alibaba | 157 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 2 | Gemini 3.1 Pro | Google DeepMind | 155 | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 3 | Qwen3.7 Max | Alibaba | 154 | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 4 | Gemini 3 Pro | Google DeepMind | 153 | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 5 | Muse Spark | Meta AI | 152 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 6 | grok-4-20 | xAI | 152 | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 7 | Gemini 3 Flash | Google DeepMind | 152 | $0.500 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 8 | Kimi K2.6 | Moonshot | 151 | $0.650 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 9 | GPT-5 Pro | OpenAI | 150 | $15.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 10 | Kimi K2.7 Code | Moonshot | 150 | $0.671 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 11 | GLM-5.1 | Z.ai (Zhipu AI) | 150 | $1.05 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 12 | Qwen 3.8 27B | Alibaba | 149 | $0.990 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 13 | Qwen 3.6 Max (Preview) | Alibaba | 149 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 14 | Grok 4.3 Beta | xAI | 149 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 15 | Kimi K2.5 | Moonshot | 148 | $0.450 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 16 | Qwen 3.6 Plus | Alibaba | 148 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 17 | Qwen3.7 Plus | Alibaba | 147 | $0.282 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 18 | MiniMax-M3 | MiniMax | 147 | $0.230 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 19 | Qwen 3.5 Plus (hosted 397B-A17B) | Alibaba | 147 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 20 | MiniMax-M2.5 | MiniMax | 147 | $0.270 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 21 | Qwen3.5 397B-A17B | Alibaba | 147 | $0.164 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 22 | Qwen3.6 27B | Alibaba | 146 | $0.150 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 23 | Grok 4 | xAI | 146 | $3.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 24 | DeepSeek-V3.2 | DeepSeek | 146 | $0.259 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 25 | nemotron-3-ultra | Nvidia | 146 | $0.500 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 26 | Kimi K2 Thinking | Moonshot | 146 | $0.550 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 27 | MiniMax-M2.7 | MiniMax | 146 | $0.210 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 28 | GLM-5 | Z.ai (Zhipu AI) | 146 | $0.600 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 29 | Gemini 2.5 Pro (Jun 2025) | Google DeepMind | 145 | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 30 | Qwen3.7 Flash | Alibaba | 145 | $0.030 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 31 | grok-4-fast | xAI | 144 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 32 | Gemini 2.5 Pro (Mar 2025) | Google DeepMind | 144 | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 33 | Qwen 3.5 Flash (hosted 35B-A3B) | Alibaba | 144 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 34 | Qwen 3.6 35B-A3B | Alibaba | 144 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 35 | Qwen3-235B-A22B-Thinking (Jul 2025) | Alibaba | 144 | $0.180 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 36 | GLM-4.7 | Z.ai (Zhipu AI) | 144 | $0.400 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 37 | Qwen 3.6 Flash | Alibaba | 143 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 38 | Gemini 2.5 Flash (Sep 2025) | Google DeepMind | 143 | $0.300 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 39 | Gemma 4 31B IT | Google DeepMind | 143 | $0.100 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 40 | Claude Opus 4 | Anthropic | 143 | $15.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 41 | qwen3.5-35b-a3b | Alibaba | 143 | $0.140 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 42 | GPT-5.5 Instant | OpenAI | 142 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 43 | Gemini 2.5 Pro (May 2025) | Google DeepMind | 142 | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 44 | Qwen3-Max | Alibaba | 142 | $0.780 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 45 | Gemma 4 26B A4B | Google DeepMind | 142 | $0.076 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 46 | Gemini 2.5 Flash (May 2025) | Google DeepMind | 142 | $0.300 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 47 | Mistral Medium 3.5 | Mistral AI | 141 | $1.50 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 48 | DeepSeek-R1 (May 2025) | DeepSeek | 141 | $0.400 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 49 | Gemini 2.5 Flash (Jun 2025) | Google DeepMind | 141 | $0.300 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 50 | Grok 3 mini | xAI | 140 | $0.250 | Epoch AI Benchmarking Hub | 2026-10-05 |
Compare all benchmarks side by side on the live leaderboard →
Among the ten highest scorers, the cheapest listed API price belongs to Gemini 3 Flash at $0.500 per million input tokens (score 152).
What Epoch ECI measures
Epoch ECI measures Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks.
How to read these scores
Higher scores are better; the scale is specific to this benchmark, so compare models only on this board. Where a model is listed at several reasoning efforts, only its highest-effort row is shown. See the methodology for how rows are chosen.
Where the data comes from
Epoch AI Benchmarking Hub (CC BY 4.0). Scores were last captured 2026-10-05; the Captured column gives each row's date.