MCP tool reference · #125 of 563 by publishers
compare_models
Exposed by 19 servers from 18 publishers, read from the live servers by the Serverdex check; most of them sit in AI & Agents; 47.4% of them take a models parameter; the most-starred is Nonobench (10 stars).
compare_models(models: array, …)Parameters
share = % of the 19 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| models | array | 47.4% | 100% | Array of 2-5 model names (e.g. ["gpt-5","claude-sonnet-4-6","gemini-3.5-flash"]) |
| ids | array | 15.8% | 100% | 2-6 OpenRouter ids, e.g. ['anthropic/claude-opus-5','openai/gpt-5.2'] |
| model_a | string | 10.5% | 100% | Display name (or substring) of the first model |
| model_b | string | 10.5% | 100% | Display name (or substring) of the second model |
| slug_a | string | 10.5% | 50% | Shorter two-model form: first model slug (use with slug_b instead of slugs). |
| slug_b | string | 10.5% | 50% | Second model slug (with slug_a). |
| a | string | 5.3% | 100% | First model slug or name |
| b | string | 5.3% | 100% | Second model slug or name |
| cached_percent | number | 5.3% | 0% | Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0) |
| calls_per_day | number | 5.3% | 0% | Calls (or agent tasks) per day |
| codes | array | 5.3% | 100% | 模型标识列表,如 ["claude-sonnet-5-5","gpt-6-sol"] |
| detail | string | 5.3% | 0% | summary (default): the short answer. full: every row as well, with source chains and photo credits. |
Source: the input schema each server returns for compare_models, aggregated over the 19 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with compare_models
19 of 19 · 18 publishers · 19 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes compare_models |
|---|---|---|---|---|---|---|
| 1 | Nonobenchmauricekleine · AI & Agents | mauricekleine | AI & Agents | 10 | yes | Side-by-side core overall and per-size accuracy, cost, latency and token results for model or family names. |
| 2 | Voicedexchandradot99 · Media & Creative | chandradot99 | Media & Creative | 1 | yes | Compare up to 6 models side by side. Each item can be an exact key "provider/type/model_id" (from search_models) or a loose name like "deepgram nova-3" or "Cartesia Sonic 3". A loose name resolves to the best match and says so in matched_as (with other_candidates): tell the user what was assumed. Unmatched items come back with "did you mean" suggestions when something is close. Ea |
| 3 | TensorFeedrippermercs · AI & Agents | rippermercs | AI & Agents | 1 | yes | PREMIUM (1 credit, $0.02). Pick between models in one call: pricing, benchmarks, status, and recent news for 2 to 5 models side by side, with cheapest-blended and per-benchmark rankings, so you choose without scraping each provider. Pay per call with an x402 wallet payment (arguments.payment, or an X-PAYMENT header; strict HTTP-402 transport at https://mcp.tensorfeed.ai/mcp?x402=strict) or use an |
| 4 | Santismm Knowledge — Harness Engineering, Agentic AI & Governancesantismm · AI & Agents | santismm | AI & Agents | 1 | yes | Put two or more frontier models side by side on the benchmark results recorded for them (score, unit, source table and evidence grade per benchmark), optionally with their rows in one profession's ranking. Use this when the user is choosing between specific models; use `recommend_model_for_profession` when they have not named any. No new aggregate is computed. Benchmarks with comparable_across_lab |
| 5 | LLMBenchmark.aitake-group · AI & Agents | take-group | AI & Agents | — | yes | Two models side by side: score on every category board where both were measured, prices, context. Names are matched loosely: 'claude opus', 'gpt-5' or a slug all work. |
| 6 | Sagelibaixingzhe · APIs & Integrations | aixingzhe | APIs & Integrations | — | yes | 对比指定模型:上下文长度、类型、输入/输出单价。传入 2–6 个模型标识。 |
| 7 | SuliHuli EV catalogsulihuli · Other | sulihuli | Other | — | yes | Side-by-side comparison of two to four electric vehicles: range (each with its test cycle), charging, battery, price and the other specs, the leading value marked per row, a short verdict, the version each column stands for, sources and cover photo credits. Each model is compared on its named version, and every figure says which version it belongs to. Use it for 'X vs Y' and 'which should I buy' q |
| 8 | Электроатласelectroatlas · IoT & Devices | electroatlas | IoT & Devices | — | yes | Сравнение двух моделей: ответ первым абзацем, таблица параметров с источниками цен, частые вопросы, фото с автором и лицензией. Звать на «что взять, X или Y», «чем отличаются». Модели — через slug_a и slug_b. EN: compare exactly two models side by side; use it for 'X or Y' questions. |
| 9 | Agent Cost Hubagentcosthub · AI & Agents | agentcosthub | AI & Agents | — | yes | Compare 2-5 models on price and (optionally) on the monthly cost of one workload. |
| 10 | IA-QA Eval & RAG — 38 toolsia-qa-com · AI & Agents | ia-qa-com | AI & Agents | — | yes | Put 2-5 AI models side by side: price per 1k tokens, context window, multimodal, reasoning, provider, pricing page. Facts only: names the cheapest and the largest context, never a "best model" — run your cases on each to choose. |
| 11 | IA-QA — 152 QA & Dev Tools for AI Agentsia-qa-com · AI & Agents | ia-qa-com | AI & Agents | — | yes | Put 2-5 AI models side by side: price per 1k tokens, context window, multimodal, reasoning, provider, pricing page. Facts only: names the cheapest and the largest context, never a "best model" — run your cases on each to choose. |
| 12 | Elétrico Levecanalthailexa-lgtm · Legal & Government | canalthailexa-lgtm | Legal & Government | — | yes | Compare two to five catalogue models side by side: specs, legal category and price. |
| 13 | Model Testedjelly-ham · AI & Agents | jelly-ham | AI & Agents | — | yes | Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 models side by side. |
| 14 | AI Waveelopstudio · AI & Agents | elopstudio | AI & Agents | — | yes | Put two or more models side by side: price, context, benchmark scores per subject, and what each costs per month at a given volume. Use this instead of calling get_model repeatedly: it aligns the fields and marks which subjects a model has not been tested on, so a missing score is not read as a low one. |
| 15 | modelrighthomezloco · AI & Agents | homezloco | AI & Agents | — | yes | Side-by-side comparison of 2-10 models by provider/slug: context window, input/output price per 1M tokens, modalities, status. |
| 16 | BenchGeckobenchgecko · Testing & QA | benchgecko | Testing & QA | — | yes | Side by side: BenchGecko score, list price, cheapest provider, context window, shared benchmark scores and Gecko Tests grades for two models. |
| 17 | Store APIkirials86-eng · AI & Agents | kirials86-eng | AI & Agents | — | yes | Ask 2 to 4 models the same question at once and get their answers side by side with token counts. Every model is billed separately. — Задать один вопрос нескольким моделям сразу и сравнить ответы. |
| 18 | operant-mcpsaagpatel · Other | saagpatel | Other | — | yes | Place two retained calculation profiles side by side by display_name substring. Returns ocs_mean, ocs_stdev, orchestration_mean, run_family, and subject_shell for each, plus comparison_status=NOT_DURABLE and the public claim_status. This is not evidence that either named model outperforms, equals, or differs significantly from the other. If a name is ambiguous or not found, returns an error listin |
| 19 | AI Pricing Hubgishh · AI & Agents | gishh | AI & Agents | — | yes | Compare pricing, context, and sourced benchmarks for model IDs. |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.