Every model in the LLMAtlas catalogue, ranked by a composite of quality, speed, context, openness and value — synced live with the OpenRouter catalogue and scored against industry benchmarks. Inspired by openrouter.ai/rankings.
Composite benchmark — MMLU-Pro, GPQA, HumanEval, SWE-bench, MATH & LMArena. Real where published, otherwise derived.
Measured throughput by provider hardware. Groq & Cerebras top the charts with LPU / wafer-scale silicon.
Log-normalised context window. 2M tokens = 100, 1M ≈ 91, 128K ≈ 64, 8K ≈ 28.
100 for fully open weights (MIT/Apache), 30 for closed/proprietary. Open = reproducible, auditable, self-hostable.
100 for free tiers, scaled inversely with price per token. Free APIs score 100; frontier-paid ~28.
Showing 50 of 201 models · ranked by composite
| # | Model | Usage | Composite | Access | |
|---|---|---|---|---|---|
12 | GR Llama 4 Maverick (Groq) Meta · Groq | 93 | FREE | ||
26 | GR Llama 4 Scout (Groq) Meta · Groq | 92 | FREE | ||
32 | NV Llama 4 Maverick 17B (128E) Meta · NVIDIA NIM | 92 | FREE | ||
43 | GI Llama 4 Maverick (free via GitHub) Meta · GitHub Models | 91 | FREE | ||
510 | GI Llama 4 Scout (free via GitHub) Meta · GitHub Models | 90 | FREE | ||
66 | PO Llama 4 Maverick (keyless) Meta · Pollinations | 90 | FREE | ||
75 | GR Llama 3.3 70B (Versatile) Meta · Groq | 89 | FREE | ||
812 | PO Llama 4 Scout (keyless) Meta · Pollinations | 89 | FREE | ||
95 | GR DeepSeek R1 Distill Llama 70B DeepSeek · Groq | 88 | FREE | ||
1010 | TO Llama 3.3 70B Turbo (free) Meta · Together AI | 88 | FREE | ||
110 | OP Llama 4 Scout Meta · OpenRouter | 88 | PAID | ||
1211 | GR Qwen3 32B (Groq) Alibaba · Groq | 88 | FREE | ||
135 | GR QwQ 32B Alibaba · Groq | 87 | FREE | ||
147 | CE GPT-OSS 120B (Cerebras) OpenAI · Cerebras | 87 | FREE | ||
158 | NV Llama 3.3 70B (NVIDIA) Meta · NVIDIA NIM | 87 | FREE | ||
1612 | NV Llama 3.3 Nemotron Super 49B Nvidia · NVIDIA NIM | 87 | FREE | ||
176 | PO DeepSeek Pro (keyless) DeepSeek · Pollinations | 87 | FREE | ||
186 | PO Qwen Large (keyless) Alibaba · Pollinations | 87 | FREE | ||
194 | PO Qwen Coder (keyless) Alibaba · Pollinations | 87 | FREE | ||
203 | DE DeepSeek V4 Flash DeepSeek · DeepSeek | 87 | FREE | ||
218 | OP Qwen 3.6 Flash Alibaba · OpenRouter | 87 | PAID | ||
221 | NV DeepSeek V4 Pro (NVIDIA) DeepSeek · NVIDIA NIM | 87 | FREE | ||
236 | NV Qwen 3.6 (NVIDIA) Alibaba · NVIDIA NIM | 87 | FREE | ||
249 | GR DeepSeek R1 Distill Qwen 32B (Groq) DeepSeek · Groq | 87 | FREE | ||
255 | OP DeepSeek V4 Flash DeepSeek · OpenRouter | 86 | PAID | ||
263 | TO Llama 4 Maverick Meta · Together AI | 86 | PAID | ||
273 | NV Llama 3.1 70B (NVIDIA) Meta · NVIDIA NIM | 86 | FREE | ||
283 | NV DeepSeek V4 Flash (NVIDIA) DeepSeek · NVIDIA NIM | 86 | FREE | ||
294 | GI Llama 3.3 70B (free via GitHub) Meta · GitHub Models | 86 | FREE | ||
301 | PO GPT-OSS 20B Fast (Pollinations, keyless) OpenAI · Pollinations | 86 | FREE | ||
311 | PO DeepSeek (keyless) DeepSeek · Pollinations | 86 | FREE | ||
320 | OP Qwen 3.6 Plus Alibaba · OpenRouter | 86 | PAID | ||
3312 | OP Llama 4 Maverick Meta · OpenRouter | 86 | PAID | ||
344 | GI DeepSeek V4 Pro (free via GitHub) DeepSeek · GitHub Models | 86 | FREE | ||
354 | CE Qwen3 32B (Cerebras) Alibaba · Cerebras | 86 | FREE | ||
360 | GR Llama 3.2 90B Vision Meta · Groq | 85 | FREE | ||
372 | OP Qwen3 Next 80B A3B (free) Alibaba · OpenRouter | 85 | FREE | ||
381 | CE GLM-4.7 (Cerebras) ZAI · Cerebras | 85 | FREE | ||
399 | NV Nemotron Nano 9B v2 Nvidia · NVIDIA NIM | 85 | FREE | ||
404 | NV Qwen3 Next 80B A3B (NVIDIA) Alibaba · NVIDIA NIM | 85 | FREE | ||
4111 | PO GLM (keyless) ZAI · Pollinations | 85 | FREE | ||
424 | OP Qwen3 Coder Flash Alibaba · OpenRouter | 85 | PAID | ||
437 | CE DeepSeek R1 Distill Qwen 32B (Cerebras) DeepSeek · Cerebras | 85 | FREE | ||
448 | GR Llama 3.1 8B Instant Meta · Groq | 84 | FREE | ||
450 | GR Llama 3.2 11B Vision Meta · Groq | 84 | FREE | ||
461 | OP Llama 3.3 70B Instruct (free) Meta · OpenRouter | 84 | FREE | ||
476 | OP GPT-OSS 20B (free) OpenAI · OpenRouter | 84 | FREE | ||
485 | OP Nemotron 3 Super 120B (free) Nvidia · OpenRouter | 84 | FREE | ||
499 | OP Qwen3 Coder (free) Alibaba · OpenRouter | 84 | FREE | ||
506 | OP GLM-4.5 Air (free) ZAI · OpenRouter | 84 | FREE |
Composite scores and capability dimensions are approximate. Benchmark values are reported from vendor cards & public evals where available, otherwise derived from the composite and flagged accordingly. Usage share, tokens/week and weekly trend are modeled estimates — OpenRouter does not expose per-model token volumes publicly. Model catalogue, pricing and context windows for OpenRouter models are synced live; 12 upcoming models are speculative projections.