AI model comparison: 17 models, three sourced facts

One model, three kinds of facts: usage heat, human preference, and list price. Each has its own source and date. No composite score.

Usage shows how often a model is called; Arena shows which answers people preferred; price shows what the vendor charges. Three separate questions — not one verdict.

This is a source-linked comparison of 17 frontier models — not a full-board ranking and not a verdict on which model is best.

17 models coveredUpdated: Arena 2026-11-06OpenRouter catalog: okOpenRouter usage rankings: access restrictedLMArena (HF dataset): failed (kept last capture)Vendor pricing pages: not run

⚠ Some sources are not connected in this release. The usage column is source-restricted; preference and prices are shown as verified. Partial board ≠ no data.

A high token count means a model is called a lot — not that it is better. Vendors count tokens differently, so cross-vendor figures are not directly comparable.

Sort by a single source's own metric only. Price sorting ranks within one currency group (CNY stays its own group; no conversion).
ModelVendorLaunchedUsage heat
Official price (in / out / cache)
Gemini 4 Carbon (High)Google—Source access restricted#11526.5[1517.1, 1535.9]4,483 votes2026-11-06Not published by vendorUnverified
Gemini 4 Argon (High)Google≈2026-10-13Source access restricted#21522.6[1517.1, 1528.2]18,399 votes2026-11-06$2 / $10 / $0.1USD·per 1M tokensLimited-time price · ≤2026-11-30Tiers2026-11-08
Muse Wonder (Max)Meta≈2026-10-12Source access restricted#31513.1[1506.6, 1519.6]11,229 votes2026-11-06$4 / $20 / $0.2USD·per 1M tokens2026-11-08
Claude Opus 5.5 (High)Anthropic≈2026-09-22Source access restricted#41505.1[1499.0, 1511.2]14,849 votes2026-11-06$4 / $20 / $0.2USD·per 1M tokensTiers2026-11-08
Claude Fable 5.1 (Max)Anthropic≈2026-09-01Source access restricted#61503.7[1498.1, 1509.2]19,892 votes2026-11-06$10 / $50 / $0.25USD·per 1M tokensTiers2026-11-08
Claude Opus 4.6 (High)Anthropic≈2026-02-04Source access restricted#71503.2[1499.9, 1506.4]85,548 votes2026-11-06$5 / $25 / $0.5USD·per 1M tokensTiers2026-11-08
Gemini 3.8 Flash (High)Google≈2026-09-02Source access restricted#91497.8[1493.6, 1502.0]59,680 votes2026-11-06$0.75 / $3.75 / $0.075USD·per 1M tokensLimited-time price · ≤2026-12-31Tiers2026-11-08
Muse Spark 1.3 (Max)Meta≈2026-09-02Source access restricted#111495.5[1490.4, 1500.6]25,672 votes2026-11-06$1.25 / $4.25 / $0.15USD·per 1M tokensTiers2026-11-08
Claude Opus 5 (Max)Anthropic≈2026-07-24Source access restricted#161489.4[1484.7, 1494.0]36,681 votes2026-11-06$5 / $25 / $0.5USD·per 1M tokensTiers2026-11-08
Gemini 3.1 Pro PreviewGoogle≈2026-02-19Source access restricted#201486.8[1483.9, 1489.7]134,284 votes2026-11-06$2 / $12 / $0.2USD·per 1M tokensTiers2026-11-08
Qwen3.8-MaxAlibaba Cloud≈2026-09-03Source access restricted#231483.0[1478.4, 1487.7]36,028 votes2026-11-06$2 / $6 / $0.25USD·per 1M tokensTiers2026-11-08
MiMo-V2.6-ProXiaomi≈2026-09-21Source access restricted#291479.5[1470.1, 1488.8]4,189 votes2026-11-06$0.435 / $0.87 / $0.0036USD·per 1M tokensTiers2026-11-08
DeepSeek V4.1 FlashNot listedDeepSeek≈2026-09-10Source access restrictedNot listed$0.3 / $1.2 / $0.006USD·per 1M tokensTiers2026-11-08
GLM-5.3Not listed智谱 BigModel≈2026-08-18Source access restrictedNot listed¥8 / ¥28 / ¥2CNY·per 1M tokensTiers2026-11-08
GPT-6.1 SolNot listedOpenAI≈2026-09-29Source access restrictedNot listed$2 / $10 / $0.1USD·per 1M tokensTiers2026-11-08
GPT-6.1 TerraNot listedOpenAI≈2026-10-26Source access restrictedNot listed$1 / $5 / $0.05USD·per 1M tokensTiers2026-11-08
Grok 4.20Not listedxAI≈2026-03-31Source access restrictedNot listed$1.25 / $2.5 / $0.2USD·per 1M tokensTiers2026-11-08

Usage heat

Token volume from OpenRouter's usage rankings, dated by window. Heat ≠ capability.

Human preference

Human-preference ratings from LMArena (Arena Score, text track), with vote counts and confidence intervals.

Official price

Per-million-token list prices from vendor pricing pages, each with source, date, currency, and conditions.

Methodology & sources →

Data sources & attribution

(No data ingested from this source in this release yet, so no snapshot date is available to cite; the line below is the required attribution wording.) Source: OpenRouter (openrouter.ai/rankings), as of not ingested — no snapshot date. Licensed under CC BY 4.0.

Data provided by OpenRouter under CC BY 4.0, AS IS; no warranties are made as to accuracy or completeness.

Adapted by AI Hot: token figures displayed as published; ordering and currency formatting applied by AI Hot.

Source: Arena Leaderboard Dataset (Arena Intelligence, Inc.), dataset lmarena-ai/leaderboard-dataset on Hugging Face, snapshot f566816dfe80f18d0bc804dd5deafa68d5957cb9, leaderboard published 2026-11-06. Licensed under CC BY 4.0. https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset

Data provided by Arena Intelligence, Inc. under CC BY 4.0, AS IS; no warranties are made as to accuracy or completeness.

Adapted by AI Hot: entries filtered to the categories shown; no scores altered.

AI Hot aggregates publicly available leaderboard data and links back to each official source. Figures reflect each source's own methodology and are not a combined or normalized ranking. Token usage reflects call volume, not model capability. Models and names belong to their respective owners.