LLM Ratings
LLM Leaderboard
Every model scored across standardized benchmarks: OpenRating Index, throughput speed, task cost economics, and input pricing. Sort any column, filter by license, and click a model for the full breakdown.
Choosing for a specific workload? See the best LLMs for coding
OpenRating Index vs input price
Input price per 1M tokens (log scale) against the OpenRating Index. Coral marks open-weights models.
Speed Index (Fastest models)
Top ten models ranked by blended output generation speed (tok/s).
Task Economics & Cost Breakdown
Standardized task compute cost broken down into active reasoning (Chain-of-Thought), prompt cache writes, cache hits, output answer, and input tokens.
Cost per Task breaks down empirical spending across standard OpenRating Index benchmark executions. Includes active reasoning tokens, prompt caching writes/hits, and input/output payload fees.
Full Model Ratings
Interactive leaderboard with live sorting and filtering.
| # | Model | License | |||||
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5 (max) Anthropic | 44.0 | 79 tok/s | $11.82 | $5 | 21.9s | Proprietary |
| 2 | GPT-6 Sol (Max) OpenAI | 44.0 | 122 tok/s | $2.47 | $2 | 34.9s | Proprietary |
| 3 | Grok 4.6 (high) xAI | 31.0 | 78 tok/s | $4.68 | $2 | 30.2s | Proprietary |
| 4 | GPT-5.6 Luna (Max) OpenAI | 24.0 | 99 tok/s | $0.33 | $0.2 | 44.5s | Proprietary |
| 5 | Kimi K3 (Low) Moonshot AI | 17.0 | 43 tok/s | $2.31 | $3 | 38.0s | Proprietary |
| 6 | Gemini 3.5 Flash-Lite | 12.0 | 311 tok/s | $0.69 | $0.3 | 4.7s | Proprietary |
| 7 | Inkling (Xhigh) (Xhigh) Inkling | 12.0 | 95 tok/s | $1.35 | $1 | 17.1s | Open weights |
| 8 | Nemotron 3 Ultra NVIDIA | 12.0 | 218 tok/s | $2.19 | $0.55 | 6.3s | Open weights |
| 9 | Claude 4.5 Haiku Anthropic | 7.0 | 91 tok/s | $0.53 | $1 | 12.9s | Proprietary |
| 10 | Nemotron 3.5 Lightning NVIDIA | 6.0 | 273 tok/s | $0.31 | $0.06 | 15.2s | Open weights |
| 11 | Muse Glimmer (high) Muse AI | 6.0 | 95 tok/s | $0.18 | $0.32 | 22.2s | Open weights |
| 12 | Mistral Medium 3.5 Mistral AI | 5.0 | 145 tok/s | $1.04 | $1.5 | 27.1s | Proprietary |
| 13 | gpt-oss-120b (High) OpenAI | 4.0 | 204 tok/s | $0.35 | $0.15 | 10.2s | Open weights |
| 14 | Gemini 2.5 Flash (Reasoning) | 0.0 | 210 tok/s | $0.00 | $0.3 | 11.4s | Proprietary |
| 15 | Nemotron 3 Super 120B A12B (Reasoning) NVIDIA | 0.0 | 131 tok/s | $0.00 | $0.3 | 32.6s | Open weights |