Kuaishou
Kling Video 3.0
Text-to-video and image-to-video with shot control and native audio.
5s output sampleNot verifiedQuote depends on settings
SpeedNot verifiedNo reviewed numeric benchmark
Official API quote not verified
COMPARE MODELS
Compare AI video generation models.
Explore video models by output settings, price conditions, and documented evidence. Check the version and provider source before you choose.
Find the right fitSources checked 2026-10-05
Sample: 5 seconds of 768P output where verified. Reference inputs cost extra. Other resolutions and audio settings are not interchangeable.
7 video models
MiniMax
MiniMax H3
Generate or edit video using text, frames, and audiovisual references.
5s output · 768P$0.4$0.08 / output second
SpeedNot verifiedNo reviewed numeric benchmark
MiniMax API · output only
MiniMax / fal.ai
MiniMax H3 Max
A speed-focused H3 variant for text, image, and reference-based video.
5s output · 768P$0.4$0.08 / output second
SpeedFaster H3 variantProvider-reported
MiniMax API · output only
ByteDance
Seedance 2.0
The quality-focused 2.0 variant for multimodal video creation and editing.
5s output sampleToken-priced$7 / 1M video tokens · no video input
SpeedNot verifiedNo reviewed numeric benchmark
BytePlus ModelArk · list rates / 1M video tokens
ByteDance
Seedance 2.0 Fast
The faster 2.0 variant for text, image, reference, and video-editing workflows.
5s output sampleToken-priced$5.6 / 1M video tokens · no video input
SpeedFaster 2.0 variantProvider-reported
BytePlus ModelArk · list rates / 1M video tokens
ByteDance
Seedance 2.0 Mini
The lower-cost 2.0 variant for video drafts, references, and editing.
5s output sampleToken-priced$3.5 / 1M video tokens · no video input
SpeedNot verifiedNo reviewed numeric benchmark
BytePlus ModelArk · list rates / 1M video tokens
ByteDance
Seedance 2.5
Audio-video generation, multimodal references, and targeted editing.
5s output sampleNot verifiedQuote depends on settings
SpeedNot verifiedNo reviewed numeric benchmark
BytePlus ModelArk · token-based video billing
Use-case tags are editorial groupings based on official capabilities. Language models earn (fast) only with a published median output speed above 150 tokens/s in the linked test settings. Video speed labels remain provider-reported. Unknown values are excluded from price bands and sorted last.
Model evaluation & benchmark research
Original research and practical experience, with short notes to help you choose.
HarnessTax: How Much Does the Harness Matter for Coding Agents?
A comparison of model–harness combinations that puts task success and cost next to each other.
Arena · Benchmark research
Announcing Artificial Analysis Capability Indices v1.1
How domain-specific benchmark slices and weights change the meaning of a model capability score.
Artificial Analysis · Evaluation methodology
Benchmarking GPT-6 Astra
A dated evaluation of GPT-6 Astra across capability, reasoning settings, token use, and task cost.
Artificial Analysis · Model evaluation
Factuality in the Arena
Why user preference alone does not settle factual accuracy, and how Arena adds factuality signals.
Arena · Evaluation methodology
Historical benchmarks · 6 models / 10 metrics
DeepSeek V4 report · Historical versions and reasoning modes
| # | Model / reasoning mode | Compare | ||||
|---|---|---|---|---|---|---|
| 01 | ✦Gemini 3.1 ProGoogle · High | 94.3 | 80.6 | 91.7 | 68.5 | |
| 02 | ◎GPT-5.4OpenAI · xHigh | 93.0 | Not reported | Not reported | 75.1 | |
| 03 | ✳Claude Opus 4.6Anthropic · Max | 91.3 | 80.8 | 88.8 | 65.4 | |
| 04 | KKimi K2.6Moonshot AI · ThinkingOpen weights | 90.5 | 80.2 | 89.6 | 66.7 | |
| 05 | DDeepSeek V4 FlashDeepSeek · MaxOpen weights | 88.1 | 79.0 | 91.6 | 56.9 | |
| 06 | ZGLM-5.1Z.ai · ThinkingOpen weights | 86.2 | Not reported | Not reported | 63.5 |
GPQA Diamond · Pass@1 % · Provider-reported data, not our own tests. Reasoning budgets may differ.Source data
Historical snapshot checked on September 24, 2026, from the DeepSeek V4 preview model card. These are provider-reported results, not our own tests or necessarily the latest model versions. Reasoning budgets and agent frameworks may differ. Unreported metrics remain unknown.
What does each metric measure?
SWE-bench Verified / Resolved %
Percentage of real GitHub issues resolved. Results depend on the agent framework, tools, and sampling setup.
GPQA Diamond / Pass@1 %
Graduate-level science questions, measured with Pass@1.
HMMT 2026 Feb / Pass@1 %
February 2026 HMMT math problems, measured with Pass@1. Do not combine with AIME or other years.
MMLU-Pro / EM %
Multidisciplinary knowledge and reasoning using exact match (EM), distinct from the original MMLU.
LiveCodeBench / Pass@1 %
Code generation using source-reported Pass@1. Missing public results are marked as not reported.
Terminal-Bench 2.0 / Accuracy %
Accuracy on multi-step terminal tasks. Results depend on the agent setup and tool permissions.
SWE-bench Pro / Resolved %
Software engineering tasks resolved, using a different task set from SWE-bench Verified.
Humanity’s Last Exam / Pass@1 %
This table uses HLE Pass@1 without tools. Do not mix it with tool-enabled results.
BrowseComp / Pass@1 %
Complex questions requiring browsing and multi-step research, measured with Pass@1.
MRCR 1M / MMR %
Multi-round retrieval over 1M-token context (MMR). Missing values mean not reported, not zero.
Imported model notebook · unreviewed historical material
MODEL NOTEBOOK
Historical model notes
8 source snapshots from DS-V4-HUUB. Unreviewed specifications are not used as current benchmark evidence.
DeepSeek V4
DeepSeek
Source snapshot · Review required →Claude Sonnet 4.7
Anthropic
Source snapshot · Review required →GPT 5.4
OpenAI
Source snapshot · Review required →Gemini 3.1 Pro
MiniMax M2.7
MiniMax
Source snapshot · Review required →Grok 4.2
xAI
Source snapshot · Review required →Qwen 3.5
Alibaba
Source snapshot · Review required →GLM 5
Zhipu AI
Source snapshot · Review required →