Sources & credits
Where the numbers come from
Every stat on every card is a published measurement. We don’t make numbers up or estimate them, and when a lab doesn’t publish a figure, the card says so. The snapshot was taken on 2026-10-11.
Benchmarks, speed and price
Intelligence, hallucination rate, context window, output speed, response time, prices and modalities come from independent public benchmark measurements of each model. Every card uses one configuration of its model (shown on the card, for example “Max” reasoning effort), so all of a card’s numbers come from the same setup. That’s why flagship reasoning models have long response times. Prices are blended 3:1 input to output; a few use the public list price from OpenRouter.
Knowledge cutoffs
From each lab’s own model docs or model cards, linked below. One date comes from a secondary source and is marked as such. Labs that don’t publish a cutoff get N/D.
Art, sound & logos
Card illustrations and shop photos were generated with StickyPrompts image generation. Music and sound effects were generated with ElevenLabs. Lab logos are from LobeHub Icons (MIT). All model names and logos are trademarks of their owners. Top Tokens is a fan-made game and isn’t affiliated with or endorsed by any AI lab.
Knowledge cutoff sources
| Card | Cutoff | Price note |
|---|---|---|
| A1 Claude Opus 5.5 | Jun 2026 | — |
| A2 GPT-6 Astra | Apr 2026 | — |
| A3 Claude Fable 5.1 | Jun 2026 | — |
| A4 Muse Spark 1.3 | Not disclosed | — |
| B1 Claude Sonnet 5.5 | Jun 2026 | — |
| B2 GPT-6.1 Sol | Apr 2026 | — |
| B3 Grok 4.7 | May 2026 | — |
| B4 Gemini 3.1 Pro | Jan 2025* | — |
| C1 Claude Haiku 5.5 | Jun 2026 | — |
| C2 Gemini 3.8 Flash | Mar 2026 | — |
| C3 GPT-6 Luna | May 2026 | — |
| C4 DeepSeek V4.1 Flash | Not disclosed | — |
| D1 Kimi K3 | Not disclosed | — |
| D2 DeepSeek V4 Pro | Not disclosed | — |
| D3 MiMo-V2.6-Pro | Not disclosed | — |
| D4 GLM-5.3 | Not disclosed | — |
| E1 Qwen3.8 Max | Not disclosed | — |
| E2 Step 5 | Not disclosed | — |
| E3 MiniMax-M3 | Jan 2026 | — |
| E4 Inkling | Jul 2026 | — |
| F1 Mercury 2.5 | Not disclosed | — |
| F2 Nemotron 3.5 Lightning | Sep 2025 | — |
| F3 Trinity Large Thinking | 2024 | — |
| F4 Gemini 3.5 Flash-Lite | Mar 2026 | — |
| G1 gpt-oss-120b | Jun 2024 | — |
| G2 Gemma 4 31B | Jan 2025 | OpenRouter list price |
| G3 Qwen3.8 27B | Not disclosed | — |
| G4 Mistral Small 4 | Nov 2024 | — |
| H1 Llama 4 Scout | Aug 2024 | — |
| H2 Command A+ | Apr 2025 | OpenRouter list price |
| H3 GPT-5.3 Codex | Aug 2025 | — |
| H4 Nova 2.0 Pro | Not disclosed | — |
* secondary source