LLM Releases

Flagship models

All reports

Frontier model leaderboard

Frontier-class models ranked by their strongest tracked benchmark, alongside context window, API price, and how each one can be accessed.

This is a reading aid, not a single-number ranking. Frontier labs report different benchmarks, so the table shows the two evals that appear most consistently across flagships — GPQA Diamond (graduate-level science reasoning) and SWE-bench Verified (resolving real GitHub issues) — and orders models by their strongest of the two.

A model near the top is not automatically “the best” for your use case: price, context window, access model, and whether a number is verified all matter. Use this to narrow the field, then open a model page for its full record.

Benchmark values are included only where the catalog has a sourced claim. Vendor figures remain self-reported until independently verified.

ModelLabAccessContextPrice (in / out)GPQASWE-benchReleasedSource
Kimi K3MoonshotModified MIT1.0M$3 / $1593.5%76.8%Jul 16, 2026source
Kimi K2.6MoonshotModified MIT256K—90.5%80.2%Mar 30, 2026source
GLM-5.2Z.aiMIT1M—91.2%-Jun 17, 2026source
Claude Opus 4.8AnthropicProprietary500K$15 / $7589%81.5%May 28, 2026source
GPT-5.6OpenAIProprietary1.5M—88.1%76.4%Jul 9, 2026source
GPT-5.4OpenAIProprietary400K—86.5%74.9%Mar 5, 2026source
GLM-5Z.aiMIT——86%77.8%Feb 11, 2026source
GLM-5.1Z.aiMIT——86.2%-Apr 8, 2026source
Grok 4.3xAIProprietary1M$1.25 / $2.586%-May 6, 2026source
Hunyuan Hy3HunyuanApache-2.0256K—-78%Jul 6, 2026source
Gemini 4 ArgonDeepMindProprietary1.0M$2 / $10--Sep 30, 2026source
GPT-6.1 SolOpenAIProprietary1.1M$2 / $10--Sep 29, 2026source
Claude Sonnet 5.5AnthropicProprietary1M$2 / $10--Sep 28, 2026source
Claude Opus 5.5AnthropicProprietary1M$4 / $20--Sep 22, 2026source
MiMo-V2.6-ProXiaomiMIT1.0M$0.435 / $0.87--Sep 21, 2026source
Grok 4.7xAIProprietary500K$2 / $6--Sep 21, 2026source
Fugu Ultra v2SakanaProprietary—$5 / $30--Sep 11, 2026source
GPT-6 Astra ProOpenAIProprietary1.1M$10 / $50--Sep 4, 2026source
GPT-6 AstraOpenAIProprietary1M$10 / $50--Sep 3, 2026source
Qwen3.8-Max-0902QwenClosed-weight (Max flagship API tier)1M$2 / $6--Sep 2, 2026source
Claude Mythos 5.1AnthropicProprietary1M—--Sep 1, 2026source
Claude Fable 5.1AnthropicProprietary1M$10 / $50--Sep 1, 2026source
Hy4 previewHunyuanApache-2.01.0M$0.834 / $2.501--Aug 28, 2026source
Ornith-1.5-397BDeepReinforceMIT——--Aug 19, 2026source
GLM-5.3Z.aiGLM-5.3 License (MIT-style; security-review gate for >$10B-revenue Model-as-a-Service providers)1.0M—--Aug 14, 2026source
Grok 4.6xAIProprietary500K$2 / $6--Aug 12, 2026source
GPT-5.6-CyberOpenAIProprietary——--Aug 10, 2026source
Qwen3.8-MaxQwenApache-2.01.0M$2 / $6--Aug 3, 2026source
Claude Opus 5AnthropicProprietary1M$5 / $25--Jul 24, 2026source
InklingThinking MachinesApache-2.01.0M$3.74 / $9.36--Jul 15, 2026source
GPT-5.6 TerraOpenAIProprietary1.5M$2.5 / $15--Jul 9, 2026source
GPT-5.6 SolOpenAIProprietary1.5M$5 / $30--Jul 9, 2026source
Muse Spark 1.1MetaProprietary1.0M$1.25 / $4.25--Jul 9, 2026source
Grok 4.5xAIProprietary—$2 / $6--Jul 8, 2026source
Claude Sonnet 5AnthropicProprietary200K$3 / $15--Jun 30, 2026source
LongCat-2.0MeituanMIT1M—--Jun 30, 2026source
Seed 2.1 ProSeedProprietary256K—--Jun 23, 2026source
Fugu UltraSakanaProprietary—$5 / $30--Jun 22, 2026source
Z.ai Fable-class modelZ.aiProprietary——--Jun 19, 2026source
Kimi K2.7 CodeMoonshotModified MIT262K$0.95 / $4--Jun 18, 2026source
MiniMax-M3MiniMaxMiniMax Community License1M—--Jun 16, 2026source
Claude Fable 5AnthropicProprietary1M$10 / $50--Jun 9, 2026source
Nemotron 3 Ultra 550B-A55BNVIDIANemotron Open Model License1M—--Jun 4, 2026source
MAI-Thinking-1MicrosoftProprietary256K—--Jun 2, 2026source
MiniMax-M2.7MiniMaxMiniMax Model License——--May 26, 2026source
Qwen3.7-MaxQwenProprietary1M$2.5 / $7.5--May 20, 2026source
Gemini 3.5 ProDeepMindProprietary2M—--May 19, 2026source
ERNIE 5.1BaiduProprietary——--May 8, 2026source
GPT-5.5-CyberOpenAIProprietary——--May 7, 2026source
GPT-5.5OpenAIProprietary800K$3 / $20--May 7, 2026source
DeepSeek V4-ProDeepSeekMIT1M—--Apr 24, 2026source
Hunyuan Hy3-previewHunyuanTencent License256K—--Apr 23, 2026source
MiMo-V2.5-ProXiaomiMIT1M—--Apr 22, 2026source
GPT-RosalindOpenAIProprietary——--Apr 16, 2026source
Muse SparkMetaProprietary——--Apr 8, 2026source
Claude Mythos 5AnthropicProprietary—$10 / $50--Apr 7, 2026source
Nemotron 3 Super 120B-A12BNVIDIANemotron Open Model License1M—--Mar 16, 2026source
Meta AvocadoMetaProprietary——--Mar 13, 2026source
Qwen3.5-397BQwenApache-2.01M—--Feb 20, 2026source
Gemini 3.1 ProDeepMindProprietary2M—--Feb 19, 2026source

Frequently asked questions

What counts as a frontier model here?

A frontier model is one a lab positions at or near the capability ceiling of the field at release — typically its flagship. LLM Releases tags this with an explicit frontier flag rather than inferring it from benchmark scores, so a model can be frontier-class even when its numbers are not yet independently verified.

Why are some benchmark cells empty?

A cell is blank when the catalog has no sourced claim for that model on that benchmark. We do not copy numbers across benchmarks or fill gaps with estimates, so a missing value means 'not reported with a source', not 'scored zero'.

Are these scores verified?

Most published figures are self-reported by the vendor under conditions they choose. We record them as claims and label them self-reported until an independent evaluation confirms the result. Treat the ranking as a starting point, then follow the source link.

Related