LMCA leaderboard: which LLMs score highest
LMCA (language-model capability assessment) currently has scores for 111 models. The top score is 68.2% by Claude Opus 5.5 (max); the median model scores 29.5% and the lowest scores 2.8%.
| # | Model | Organisation | LMCA score | Cheapest input $/M | Source | Captured |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 (max) | Anthropic | 68.2% | $4.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 2 | Claude Opus 5 (max) | Anthropic | 63.3% | $5.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 3 | Claude Fable 5 (max) | Anthropic | 60.3% | $10.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 4 | GPT-5.6 Sol (pro, max) | OpenAI | 59.2% | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 5 | GPT-6 Sol (max) | OpenAI | 59.1% | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 6 | GPT-5.6 Sol (max) | OpenAI | 58.4% | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 7 | Claude Opus 4.6 (max) | Anthropic | 55.8% | $5.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 8 | GPT-5.6 Terra (max) | OpenAI | 55.0% | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 9 | GPT-5.5 (xhigh) | OpenAI | 54.3% | $5.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 10 | GPT-5.5 Pro (xhigh) | OpenAI | 53.9% | $30.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 11 | Kimi K3 (max) | Moonshot | 52.7% | $1.29 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 12 | Claude Opus 4.7 (max) | Anthropic | 52.2% | $5.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 13 | GPT-5.4 (xhigh) | OpenAI | 52.0% | $2.50 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 14 | Gemini 3.7 Flash (high) | Google DeepMind | 50.4% | $0.750 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 15 | Muse Spark 1.1 (high) | Meta AI | 49.9% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 16 | Claude Sonnet 5 (max) | Anthropic | 49.3% | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 17 | GPT-5.6 Luna (max) | OpenAI | 48.5% | $0.200 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 18 | Grok 4.6 (xhigh) | xAI | 48.5% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 19 | Muse Spark 1.2 (xhigh) | Meta AI | 48.4% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 20 | Claude Sonnet 4.6 (max) | Anthropic | 46.5% | $3.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 21 | Qwen3.8 Max (xhigh) | Alibaba | 46.2% | $1.65 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 22 | Grok 4.5 (high) | xAI | 45.2% | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 23 | GPT-6 Luna (max) | OpenAI | 44.5% | $0.100 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 24 | Qwen3.7 Max | Alibaba | 44.0% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 25 | GPT-5.2 (xhigh) | OpenAI | 43.9% | $1.75 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 26 | GPT-5.1 (high) | OpenAI | 43.9% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 27 | Qwen 3.6 Max (Preview) | Alibaba | 42.5% | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 28 | DeepSeek V4 Flash 0731 (max) | DeepSeek | 41.7% | $0.015 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 29 | DeepSeek v4 Pro (max) | DeepSeek | 41.2% | $0.435 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 30 | GPT-5.4 mini (xhigh) | OpenAI | 40.8% | $0.750 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 31 | GPT-5 (high) | OpenAI | 40.0% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 32 | o3 (high) | OpenAI | 39.7% | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 33 | Gemma 4 31B IT | Google DeepMind | 39.2% | $0.100 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 34 | grok-4-20 | xAI | 38.7% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 35 | o3-pro-2025-06-10 (high) | OpenAI | 38.5% | $20.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 36 | grok-4.3 (high) | xAI | 38.3% | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 37 | Qwen3.5 397B-A17B | Alibaba | 37.9% | $0.164 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 38 | Inkling (xhigh) | Thinking Machines | 37.6% | $0.950 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 39 | Qwen3.7 Plus | Alibaba | 37.6% | $0.282 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 40 | Claude Opus 4 | Anthropic | 37.4% | $15.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 41 | Kimi K2.6 | Moonshot | 37.3% | $0.650 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 42 | Claude Opus 4.1 (unknown thinking) | Anthropic | 37.1% | $15.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 43 | nemotron-3-ultra | Nvidia | 36.9% | $0.500 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 44 | GPT-5.4 nano (xhigh) | OpenAI | 36.9% | $0.200 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 45 | Qwen3.5 Plus | Alibaba | 36.4% | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 46 | DeepSeek v4 Flash (max) | DeepSeek | 35.9% | $0.090 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 47 | Qwen3.6 27B | Alibaba | 34.5% | $0.150 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 48 | GPT-5 mini (high) | OpenAI | 34.2% | $0.250 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 49 | Qwen3.5 27B | Alibaba | 34.0% | $0.195 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 50 | MiniMax-M3 | MiniMax | 33.7% | $0.230 | 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 GPT-5.6 Sol (pro, max) at $2.00 per million input tokens (score 59.2%).
What LMCA measures
LMCA measures language-model capability assessment.
How to read these scores
Scores are percentages (higher is better): the share of questions or tasks the model completed correctly. 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.