Skip to main content
Van Data Team

AI model benchmark sources

The AI model benchmarks are built from 221 source records: 20 independent sources from 5 publishers, which every benchmark score comes from, and 201 official pages from 30 publishers, which support each model record as a whole.

Each record names its publisher, the date it was last verified, its dataset version and license where the publisher states one, what it covers and how the data uses it. Missing metadata is not filled or inferred. Dataset version 2026-10-29, last verified 2026-10-29.

Independent benchmark sources (20)

Independent sources come from publishers separate from the model providers. Every benchmark score on the pages comes from one of them, read from a dated snapshot.

Arena 6

  • Arena leaderboard dataset (lmarena-ai/leaderboard-dataset)

    Covers benchmark · Verified 2026-10-12 · Version lmarena-ai/leaderboard-dataset@e16f9023298691b4596eca61b4e31161dff31200 · License CC-BY-4.0

    Ratings from blind pairwise human votes, published by Arena (formerly LMArena) in its public leaderboard dataset and pinned here to one commit. The overall category of the latest split is used; for text, the style-controlled leaderboard, which is the default view on arena.ai. A model maps only when its Arena row names the same model; where Arena lists several quality or resolution settings of one model, the best rated row is used and recorded in sourceRow. Ratings are rounded to whole points. Credit: Arena, lmarena-ai/leaderboard-dataset on Hugging Face, CC BY 4.0.

  • Arena Text-to-Image leaderboard

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    People compare two anonymous images generated from the same prompt and vote for the better one. Arena fits a Bradley-Terry model to the votes and reports ratings on an Elo-like scale.

  • Arena Image Edit leaderboard

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    People compare two anonymous edits of the same image from the same instruction and vote for the better one. Arena fits a Bradley-Terry model to the votes and reports ratings on an Elo-like scale.

  • Arena Text-to-Video leaderboard

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    People compare two anonymous videos generated from the same prompt and vote for the better one. Arena fits a Bradley-Terry model to the votes and reports ratings on an Elo-like scale.

  • Arena Image-to-Video leaderboard

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    People compare two anonymous videos animated from the same image and prompt and vote for the better one. Arena fits a Bradley-Terry model to the votes and reports ratings on an Elo-like scale.

  • Arena Text leaderboard

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    People put the same prompt to two anonymous models and vote for the better answer. Arena fits a Bradley-Terry model to the votes; the rating used here is the style-controlled one, which is the default view on arena.ai.

Artificial Analysis 5

  • Artificial Analysis Speech Arena leaderboard (text to speech)

    Covers benchmark · Verified 2026-10-13 · Version Provider voice leaderboard, read 2026-10-13 · License Artificial Analysis Terms of Use

    Listeners compare two anonymous clips of the same text and vote for the more natural one; Artificial Analysis fits Elo ratings to the votes, using each provider's own voices. Cited with a link as Artificial Analysis asks; its terms reserve redistribution, so these scores are shown on the page and left out of the dataset download.

  • Artificial Analysis speech-to-text leaderboard (AA-WER v2, non-streaming)

    Covers benchmark · Verified 2026-10-13 · Version AA-WER v2, read 2026-10-13 · License Artificial Analysis Terms of Use

    Artificial Analysis transcribes the same held-out audio through each provider API and reports the weighted word error rate. Cited with a link as Artificial Analysis asks; its terms reserve redistribution, so these scores are shown on the page and left out of the dataset download.

  • Artificial Analysis speech-to-text leaderboard (AA-WER Streaming)

    Covers benchmark · Verified 2026-10-13 · Version AA-WER Streaming, read 2026-10-13 · License Artificial Analysis Terms of Use

    Artificial Analysis streams the same held-out audio through each provider realtime API and reports the word error rate of the final transcript. Cited with a link as Artificial Analysis asks; its terms reserve redistribution, so these scores are shown on the page and left out of the dataset download.

  • Artificial Analysis Video Arena leaderboard (AA-Video-T2V v2.0)

    Covers benchmark · Verified 2026-10-13 · Version AA-Video-T2V v2.0, read 2026-10-13 · License Artificial Analysis Terms of Use

    People compare two anonymous videos generated from the same prompt and vote for the better one; Artificial Analysis fits Elo ratings to the votes. Cited with a link as Artificial Analysis asks; its terms reserve redistribution, so these scores are shown on the page and left out of the dataset download.

  • Artificial Analysis Video Arena leaderboard (AA-Video-I2V v1.0)

    Covers benchmark · Verified 2026-10-13 · Version AA-Video-I2V v1.0, read 2026-10-13 · License Artificial Analysis Terms of Use

    People compare two anonymous videos animated from the same image and prompt and vote for the better one; Artificial Analysis fits Elo ratings to the votes. Cited with a link as Artificial Analysis asks; its terms reserve redistribution, so these scores are shown on the page and left out of the dataset download.

Epoch AI 4

  • Epoch AI Benchmarking Hub data (benchmark_data.zip)

    Covers benchmark · Verified 2026-10-12 · Version benchmark_data.zip retrieved 2026-10-12, sha256 prefix 2fb16ca26aea846c · License CC-BY-4.0

    Results Epoch AI ran itself (the GPQA Diamond, FrontierMath Tiers 1-3 v2 and SimpleQA Verified files), not the external files it collects from other publishers. A model maps only when its Epoch row is unambiguous: exact name, or a dated version pinned by the record release date. Where Epoch lists several reasoning-effort settings, the best published configuration is used and its row is recorded in sourceRow. Scores are converted from 0-1 to 0-100 and rounded to one decimal. Epoch evaluated rows between 2023 and 2026-10-09; every result is dated to this capture. Credit: Epoch AI, Capabilities and benchmarking, epoch.ai, CC BY 4.0.

  • GPQA Diamond benchmark (Epoch AI)

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    198 four-option graduate-level questions in biology, physics and chemistry, written by domain experts; random guessing scores 25%. Epoch runs the evaluation itself.

  • FrontierMath benchmark (Epoch AI)

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    Original research-level mathematics problems written and vetted by expert mathematicians. Tiers 1-3 v2 (released 2026-06-12) is the 295-problem base set after a revision that corrected errors in 42% of problems. Scores come from Epoch-run private sets. OpenAI funded the benchmark and has access to part of it.

  • SimpleQA Verified benchmark (Epoch AI)

    Covers benchmark · Verified 2026-10-12 · Not versioned · License CC-BY-4.0

    A 1,000-question factoid benchmark from Google, building on SimpleQA from OpenAI. Epoch runs it itself and reports the proportion answered correctly, not the F1-based score Google reports.

LiveBench 4

  • LiveBench category-weighted averaging implementation

    Covers benchmark · Verified 2026-08-07 · Version LiveBench-2026-06-25@19e766a5de4de07d672ed5bf9f0a69ceed1d39bf · License Apache-2.0

    Pinned implementation averages task scores within each of the seven categories, then averages the category scores; the paired categories_2026_06_25.json file defines category membership.

  • LiveBench 2026-06-25 task results

    Covers benchmark · Verified 2026-08-07 · Version LiveBench-2026-06-25@19e766a5de4de07d672ed5bf9f0a69ceed1d39bf · License Apache-2.0

    Snapshot and measurement date: 2026-06-25. Overall scores are imported only for unambiguous model mappings and are recomputed with the pinned category-weighted averaging implementation.

  • LiveBench datasheet and methodology

    Covers benchmark · Verified 2026-08-06 · Version LiveBench-2024-11-25 · License Apache-2.0

    Primary benchmark documentation confirms objective scoring, public distribution, and Apache 2.0 reuse terms.

  • LiveBench 2024-11-25 task results

    Covers benchmark · Verified 2026-08-06 · Version LiveBench-2024-11-25@347e3d0b6a4916cd66f8bda31ce7ecdd7436ecc3 · License Apache-2.0

    Snapshot and measurement date: 2024-11-25. Exact published snapshot; only direct Web of Lies V2 percentages with unambiguous model mappings are imported.

OpenRouter 1

  • OpenRouter models API catalogue

    Covers identity, pricing · Verified 2026-09-09 · Not versioned · License not stated

    Third-party API catalogue used only to cross-check published token prices, context limits, and listing dates against first-party documentation.

Official provider sources (201)

Official sources come from the model providers themselves. They support each model record as a whole: they are not a field-by-field audit trail.

Google 39

  • Gemini API release notes

    Covers identity · Verified 2026-10-13 · Not versioned · License CC-BY-4.0

    Official release notes verify the dated Gemini 3.5 Flash, Gemini 3.1 Flash Live, Gemini 3.1 Flash TTS, Gemini 3.1 Flash Lite Image, Gemini 3 Pro Image, and Gemini Omni Flash releases represented in this catalog.

  • Gemini 3.5 Flash model

    Covers identity · Verified 2026-08-07 · Not versioned · License CC-BY-4.0

    Official model documentation verifies model code, modalities, and token limits; exact token prices remain unreported here.

  • Gemini 3.6 Flash model

    Covers identity · Verified 2026-08-07 · Not versioned · License CC-BY-4.0

    Official model documentation verifies model code, 2026-07-21 update, modalities, and token limits.

  • Using the latest Gemini models

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License CC-BY-4.0

    Official latest-model guidance verifies the exact standard input/output prices represented for Gemini 3.6 Flash.

  • Gemini 3.5 Flash-Lite model

    Covers identity · Verified 2026-08-07 · Not versioned · License CC-BY-4.0

    Official model documentation verifies the stable model code, multimodal inputs, token limits, capabilities, and July 2026 update.

  • Gemini 3.5 Flash-Lite pricing

    Covers pricing · Verified 2026-08-07 · Not versioned · License CC-BY-4.0

    Official pricing table verifies the standard paid-tier input, cached-input, and output rates represented here.

  • Gemini Developer API pricing

    Covers pricing · Verified 2026-10-23 · Not versioned · License not stated

    Official Gemini Developer API pricing table used only for exact published token, image, audio-minute, and video-second prices represented in model records.

  • Gemini 3.1 Flash Image pricing

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

    First-party pricing table used to verify Gemini 3.1 Flash Image standard token and resolution-specific image prices.

  • Gemini native image generation capabilities

    Covers identity · Verified 2026-08-10 · Not versioned · License not stated

    First-party native image guide used to verify Gemini 3.1 Flash Image generation, editing, image input, and mixed text/image output capabilities.

  • Gemini 3.7 Flash model

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Official model documentation verifies the stable Gemini 3.7 Flash code, text/image/video/audio inputs, text output, token limits, structured outputs, thinking, and URL context.

  • Introducing Gemini 3.7 Flash

    Covers identity, pricing · Verified 2026-08-18 · Not versioned · License not stated

    Official Google announcement verifies the 2026-08-13 release, coding and agent positioning, and introductory token prices through 2026-12-31 before the documented 2027 rate change.

  • Gemini 3.1 Pro Preview

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the Gemini 3.1 Pro Preview endpoint, multimodal inputs, text output, token limits, and documented capabilities.

  • Gemini 3 Flash Preview

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the Gemini 3 Flash Preview endpoint, multimodal inputs, text output, token limits, and documented capabilities.

  • Gemini 3.1 Flash-Lite

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the stable Gemini 3.1 Flash-Lite endpoint, multimodal inputs, text output, token limits, and documented capabilities.

  • Gemini 3.5 Live Translate

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the Gemini 3.5 Live Translate preview endpoint, audio input, translated-audio and transcript output, and token limits.

  • Gemini Live API

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Live API guide verifies realtime audio model operation and the preview endpoint lifecycle applies to the live-model records.

  • Gemini 3.1 Flash Live Preview

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the Gemini 3.1 Flash Live preview endpoint, supported realtime multimodal inputs, text and audio output, token limits, and capabilities.

  • Gemini 3.1 Flash TTS Preview

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the Gemini 3.1 Flash TTS preview endpoint, text input, audio output, token limits, and audio generation capability.

  • Text-to-speech generation

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Text-to-Speech guide verifies controllable speech generation and streaming support for the Gemini 3.1 Flash TTS preview endpoint.

  • Gemini 3.1 Flash Lite Image

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the stable Gemini 3.1 Flash Lite Image endpoint, text and image inputs, text and image output, token limits, and image generation and editing capabilities.

  • Gemini 3 Pro Image

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Model card verifies the stable Gemini 3 Pro Image endpoint, text and image inputs and outputs, token limits, and image generation capability.

  • Gemini Omni Flash

    Covers identity · Verified 2026-10-13 · Not versioned · License CC-BY-4.0

    Model card verifies the Gemini Omni Flash preview endpoint, text, image, and video inputs, video output, context window, and 3-to-10-second output range.

  • Generate and edit videos with Gemini Omni Flash

    Covers identity · Verified 2026-10-13 · Not versioned · License CC-BY-4.0

    Gemini Omni Flash guide verifies preview lifecycle, conversational video editing, native multimodal context, and generated video with audio.

  • Gemini deprecations

    Covers identity · Verified 2026-08-18 · Not versioned · License CC-BY-4.0

    Lifecycle table verifies published stable or preview status and announced shutdown dates only for the Gemini endpoints that reference it.

  • Gemini Nano Banana 2.1

    Covers identity · Verified 2026-10-12 · Not versioned · License not stated

    Stable model gemini-nano-banana-2.1: text, image, video and PDF input; image and text output; 1K, 2K and 4K output.

  • Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking

    Covers identity · Verified 2026-10-12 · Not versioned · License not stated

    Two speech-to-speech models for the Gemini API and Google AI Studio.

  • Gemini 3.8 text-to-speech models

    Covers identity · Verified 2026-10-12 · Not versioned · License not stated

    Gemini 3.8 Flash TTS and Flash-Lite TTS announcement.

The 6 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

The 4 records below: Official provider documentation used to verify model identity and release details.

The 2 records below: Official provider documentation used to verify exact model specifications.

  • Gemini API models

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Gemini 2.5 Pro

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

OpenAI 29

  • GPT-5.4 model

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official model documentation verifies the dated snapshot, token limits, modalities, and exact standard token prices represented here.

  • Introducing GPT-5.5

    Covers identity · Verified 2026-08-07 · Not versioned · License not stated

    Official release announcement verifies model identity and the 2026-04-23 release date.

  • GPT-5.5 model

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official model documentation verifies token limits, modalities, and exact standard token prices represented here.

  • GPT-5.6: Frontier intelligence that scales with your ambition

    Covers identity · Verified 2026-08-07 · Not versioned · License not stated

    Official release announcement verifies the Sol, Terra, and Luna identities and 2026-07-09 general-availability date.

  • OpenAI GPT-5.6 model catalog

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official model catalog verifies the Sol, Terra, and Luna token limits, modalities, roles, and exact standard token prices represented here.

  • OpenAI API pricing

    Covers pricing · Verified 2026-08-06 · Not versioned · License not stated

    Official pricing page used only for the exact token prices represented in model records.

  • GPT-Live 1 model

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

    Full-duplex voice model; audio and text in and out; $0.05 per voice-session minute billed per second; reasoning and tools delegated to a separately billed backend model.

  • OpenAI API changelog

    Covers identity · Verified 2026-10-13 · Not versioned · License not stated

    Release dates: gpt-image-2.5-sunburst and gpt-image-2.5-flare 2026-09-08; gpt-live-1 generally available 2026-09-10.

  • GPT Image 2.5 Sunburst model

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

    Most capable image generation and editing model; token rates match GPT Image 2.

  • GPT Image 2.5 Flare model

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

    Fastest model for everyday image generation; token rates match GPT Image 2.

The 10 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

  • GPT Image 2 model

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

  • GPT-Realtime-1.5 model

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

  • gpt-audio-1.5 model

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

  • GPT-4o Transcribe model

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

  • TTS-1 model

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

  • GPT-6 Astra model reference

    Covers identity, pricing · Verified 2026-09-09 · Not versioned · License not stated

  • OpenAI API pricing

    Covers pricing · Verified 2026-10-13 · Not versioned · License not stated

  • GPT-Realtime-2 model

    Covers identity, pricing · Verified 2026-10-13 · Not versioned · License not stated

  • GPT Transcribe model

    Covers identity, pricing · Verified 2026-10-13 · Not versioned · License not stated

  • GPT-6.1 Terra model reference

    Covers identity, pricing · Verified 2026-10-28 · Not versioned · License not stated

The 4 records below: Official provider documentation used to verify exact model specifications.

  • GPT-4o model

    Covers identity, pricing · Verified 2026-08-06 · Not versioned · License not stated

  • GPT-4.1 model

    Covers identity, pricing · Verified 2026-08-06 · Not versioned · License not stated

  • GPT-4.1 mini model

    Covers identity, pricing · Verified 2026-08-06 · Not versioned · License not stated

  • GPT-4.1 nano model

    Covers identity, pricing · Verified 2026-08-06 · Not versioned · License not stated

The 3 records below: 1.05M context, 128K max output, knowledge cutoff 2026-02-16, six reasoning-effort levels.

  • GPT-5.6 Sol model

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

  • GPT-5.6 Terra model

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

  • GPT-5.6 Luna model

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

The 2 records below: Official provider documentation used to verify model identity and release details.

SpaceXAI 14

  • Grok 4.3 model

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official model documentation verifies Grok 4.3 modalities, context window, reasoning modes, aliases, and standard short-context prices.

  • xAI inference models API reference

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official API reference exposes Grok 4.3 modalities, aliases, and token pricing fields; its object creation timestamp is not treated as a public release date.

  • Skills in web, iOS, and Android

    Covers identity · Verified 2026-08-07 · Not versioned · License not stated

    Official 2026-05-18 announcement confirms Grok 4.3 was live across grok.com, iOS, and Android by that date; it is not treated as the model's exact release date.

  • SpaceXAI API release notes

    Covers identity · Verified 2026-08-07 · Not versioned · License not stated

    Official release notes verify Grok 4.20 and Grok 4.20 Multi-agent API availability on 2026-03-10.

  • Grok 4.20 System Card

    Covers identity · Verified 2026-08-07 · Version 2026-04-07 · License not stated

    Official system card verifies Grok 4.20 identity, single-agent and multi-agent deployment modes, supported input modalities, and intended uses.

  • SpaceXAI model pricing

    Covers identity, pricing · Verified 2026-08-14 · Not versioned · License not stated

    Official current pricing table verifies active Grok 4.6, Grok 4.5, and Grok 4.20 variants, their documented context windows, and standard and long-context token rates.

  • Grok model retirement on May 15, 2026

    Covers identity · Verified 2026-08-07 · Not versioned · License not stated

    Official lifecycle notice verifies Grok 3 retirement and redirect to Grok 4.3, and identifies Grok 4.3 as the recommended general replacement.

  • Introducing Grok 4.5

    Covers identity · Verified 2026-08-07 · Not versioned · License not stated

    Official announcement verifies the model identity, release date, and intended coding, agentic, and knowledge-work scope.

  • Grok 4.5 model

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official model documentation verifies modalities, context window, and standard short-context token prices; the model caution discloses higher long-context rates.

  • Introducing Grok 4.6

    Covers identity · Verified 2026-08-14 · Not versioned · License not stated

    Official announcement verifies the 2026-08-12 release date and positioning for long-running agents, coding, and knowledge work.

  • Grok 4.6 model

    Covers identity, pricing · Verified 2026-08-14 · Not versioned · License not stated

    Official model documentation verifies the exact model ID, text and image input, text output, 500,000-token context window, reasoning, function calling, structured outputs, and standard token prices.

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

  • grok-imagine-image model

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

  • Video generation

    Covers identity · Verified 2026-08-10 · Not versioned · License not stated

  • Imagine API pricing

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

Anthropic 12

  • Introducing Claude Opus 4.8

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official release documentation verifies model identity, release date, the published context window, and standard input/output pricing.

  • Introducing Claude Sonnet 5

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official release documentation verifies model identity, release date, API availability, and introductory pricing through 2026-08-31.

  • Claude Fable 5 and Claude Mythos 5

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official release announcement verifies Claude Fable 5 identity, 2026-06-09 release date, API access, standard token pricing, and general availability after redeployment.

  • Claude models overview

    Covers identity, pricing · Verified 2026-08-07 · Not versioned · License not stated

    Official current-model documentation verifies Fable's text-and-image inputs, 1,000,000-token context window, 128,000-token output limit, and current API availability.

  • Claude pricing

    Covers pricing · Verified 2026-08-06 · Not versioned · License not stated

    Official pricing documentation used only for the exact token prices represented in model records.

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

The 2 records below: Official provider documentation used to verify model identity and release details.

The 2 records below: Official provider documentation used to verify exact model specifications.

  • Claude 3 Haiku

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Claude models overview

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

xAI 12

  • xAI models and pricing

    Covers identity, pricing · Verified 2026-10-11 · Not versioned · License not stated

    Official model catalog used to verify documented model availability and pricing fields, not historical release dates.

  • grok-imagine-video-1.5-lite

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

    Text and image to video at $0.020 per output second; batch API supported.

The 6 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

The 4 records below: Official provider documentation used to verify model identity and release details.

  • Announcing Grok-1.5

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Grok-1.5 Vision Preview

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Grok-2 Beta Release

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Grok 3 Beta

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

DeepSeek 11

  • DeepSeek API pricing

    Covers pricing · Verified 2026-10-13 · Not versioned · License not stated

    Official pricing documentation consulted for price provenance; unavailable exact values remain unreported.

  • DeepSeek-V4.1-Flash release

    Covers identity · Verified 2026-10-12 · Not versioned · License not stated

    Official release note, 2026-09-10: 552B-parameter MoE with native visual understanding; 8B active parameters for input and 16B for output.

  • DeepSeek-V4.1-Flash model weights

    Covers identity · Verified 2026-10-12 · Not versioned · License not stated

    Official open-weights repository, created 2026-09-10, MIT licence, image-text-to-text.

  • DeepSeek-V4.1-Flash-1017

    Covers identity · Verified 2026-10-23 · Not versioned · License not stated

    Official release note, 2026-10-17: a minor update served under the same API name at unchanged prices.

  • DeepSeek-V4.1-Flash-1017 model weights

    Covers identity · Verified 2026-10-23 · Not versioned · License not stated

    Official open-weights repository, MIT licence, image-text-to-text, 1M-token context.

The 4 records below: Official provider documentation used to verify model identity and release details.

  • DeepSeek-V2

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • DeepSeek-Coder-V2

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • DeepSeek-V3

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • DeepSeek-R1

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Meta 10

  • Introducing Muse Spark Open

    Covers identity · Verified 2026-10-23 · Not versioned · License not stated

    Official announcement, 2026-10-15: 816B total and 42B active parameters, 1M-token context, weights under the Muse Model License.

  • Muse Spark Open model card

    Covers identity · Verified 2026-10-23 · Not versioned · License not stated

    Official open-weights repository: text, image, video and audio in, text out; no first-party API.

The 5 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

The 3 records below: Official provider documentation used to verify model identity and release details.

  • Introducing Meta Llama 3

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Introducing Llama 3.1

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Llama 3.2

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

Mistral AI 10

  • Mistral AI pricing

    Covers pricing · Verified 2026-08-06 · Not versioned · License not stated

    Official pricing page consulted for price provenance; unavailable exact values remain unreported.

  • Introducing Mistral Large 4

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

    Public preview announced 2026-10-06 at $1.36 / $4.18 per 1M input / output tokens; weights promised by the end of October.

  • Mistral Large 4 model card

    Covers identity, pricing · Verified 2026-10-12 · Not versioned · License not stated

    Model id mistral-large-4-0, public preview, 1M context, 1.05T total and 52B active parameters, 1.6B vision encoder.

The 4 records below: Official provider documentation used to verify model identity and release details.

  • Codestral

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Large Enough

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Announcing Pixtral 12B

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Un Ministral, des Ministraux

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

  • Voxtral 3

    Covers identity, pricing · Verified 2026-10-23 · Not versioned · License not stated

  • Voxtral Small Transcribe 3

    Covers identity, pricing · Verified 2026-10-23 · Not versioned · License not stated

  • Voxtral TTS 3

    Covers identity, pricing · Verified 2026-10-23 · Not versioned · License not stated

Alibaba Cloud 6

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Moonshot AI 6

The 3 records below: Official provider documentation used to verify model identity and release details.

  • Kimi-VL

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Kimi-Dev

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

  • Kimi K2

    Covers identity · Verified 2026-08-06 · Not versioned · License not stated

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

ElevenLabs 5

The 5 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

NVIDIA 5

The 5 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Microsoft 4

The 4 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Xiaomi 4

The 4 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Z.ai 4

The 4 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Inception 3

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

MiniMax 3

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Qwen Team 3

The 3 records below: Official provider documentation used to verify model identity and release details.

Reflection AI 3

The 3 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Black Forest Labs 2

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

BytePlus 2

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Cartesia 2

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

  • Cartesia TTS models

    Covers identity · Verified 2026-10-13 · Not versioned · License not stated

  • Cartesia pricing

    Covers pricing · Verified 2026-10-13 · Not versioned · License not stated

Elorian 2

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

IBM 2

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Microsoft AI 2

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

StepFun 2

The 2 records below: First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Alibaba Qwen 1

  • Qwen3.8-Flash-Next model card

    Covers identity · Verified 2026-10-13 · Not versioned · License not stated

    First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Runway 1

  • Available AI Models

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

    First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Stability AI 1

  • Stability AI Developer Platform pricing

    Covers identity, pricing · Verified 2026-08-10 · Not versioned · License not stated

    First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Upstage 1

  • Solar Pro 4 documentation

    Covers identity, pricing · Verified 2026-10-13 · Not versioned · License not stated

    First-party provider documentation used only for the stated model identity, capabilities, lifecycle, access, and pricing.

Reuse the data: JSON · CSV. How the records are read, and why a benchmark winner may not fit production, is in the methodology.